# MLOps Talks > Summaries of talks, podcast episodes and meetups from the MLOps Community YouTube channel, now AAIF Live (https://www.youtube.com/@AAIFLive-x1r). Each page has a three-bullet TL;DR, a summary, five to nine key ideas with links into the video at the second they start, quotes, and tags. Curated packs put sessions in a deliberate order. Every talk page and pack page also exists as plain Markdown: add .md to any talk or pack URL, or send Accept: text/markdown to the same URL. ## Packs - [From notebook to production](https://mlopstalks.com/packs/from-notebook-to-production): The model works when you run the notebook. - [Reproducible experiments](https://mlopstalks.com/packs/reproducible-experiments): The score is in a spreadsheet, the model is in a bucket, and nobody can identify the data or environment that produced either. - [Data quality for machine learning](https://mlopstalks.com/packs/data-quality-for-machine-learning): A table loads successfully and still gives the model the wrong evidence. - [Feature engineering and feature stores](https://mlopstalks.com/packs/feature-engineering-and-feature-stores): Two models use a feature with the same name, but different calculations. - [Training pipelines and orchestration](https://mlopstalks.com/packs/training-pipelines-and-orchestration): The preprocessing finished, but training never started. - [Testing machine learning systems](https://mlopstalks.com/packs/testing-machine-learning-systems): Your code tests pass and the new model scores better, but an important customer scenario has got worse. - [CI/CD for machine learning](https://mlopstalks.com/packs/ci-cd-for-machine-learning): A rollback restores yesterday's model weights behind today's incompatible serving code. - [Model serving in production](https://mlopstalks.com/packs/model-serving-in-production): A model that predicts quickly on your laptop can still leave users waiting. - [Monitoring and drift](https://mlopstalks.com/packs/monitoring-and-drift): The endpoint is healthy, yet recommendations are empty or one customer group receives worse predictions. - [Feedback loops and retraining](https://mlopstalks.com/packs/feedback-loops-and-retraining): Production errors keep arriving, but the next model trains on the same old examples. - [Scaling training and compute](https://mlopstalks.com/packs/scaling-training-and-compute): Adding GPUs made training more expensive, but barely shortened the run. - [The cost of production ML](https://mlopstalks.com/packs/the-cost-of-production-ml): The bill is growing, but buying cheaper machines is only one possible response. - [ML governance in practice](https://mlopstalks.com/packs/ml-governance-in-practice): Nobody can name all the models in production. - [Security and privacy for ML systems](https://mlopstalks.com/packs/security-and-privacy-for-ml-systems): A downloaded model brings executable code into your environment. - [ML platforms people actually use](https://mlopstalks.com/packs/ml-platforms-people-actually-use): You built the platform, but data scientists still run their own scripts and ask colleagues how to deploy. - [Build versus buy](https://mlopstalks.com/packs/build-versus-buy): The prototype works, but nobody budgeted for the years of upgrades behind it. - [How ML teams ship together](https://mlopstalks.com/packs/how-ml-teams-ship-together): The model is ready, but the application team has no time to integrate it. - [RAG in production](https://mlopstalks.com/packs/rag-in-production): The answer is somewhere in your documents, but retrieval misses it. - [Evaluating LLM applications](https://mlopstalks.com/packs/evaluating-llm-applications): A prompt change looks better on your favorite examples but annoys real users. - [Agents in production](https://mlopstalks.com/packs/agents-in-production): An agent calls the right API but changes the wrong record. - [Running open models](https://mlopstalks.com/packs/running-open-models): The model runs on your GPU, but concurrent requests exhaust its memory. - [Fine-tuning for a real task](https://mlopstalks.com/packs/fine-tuning-for-a-real-task): The fine-tuned model sounds more like your examples, but the business decision is no better. ## Talks - [Agentic DX: Bringing IDP into your IDE](https://mlopstalks.com/talks/agentic-dx-bringing-idp-into-your-ide): Adnan Vahora, Motorola Solutions. Adnan Vahora describes how Motorola Solutions tried to increase adoption of an Internal Developer Platform used by more than 4,000 monthly active users. The platform... - [Before the Agent Calls: Source-level Findings from 100 MCP Servers](https://mlopstalks.com/talks/before-the-agent-calls-source-level-findings-from-100-mcp-servers): Akash Sathish, Sahaj Software. Akash Sathish examines MCP security before an agent makes its first tool call. He describes how malicious instructions can enter through prompts, connected MCP servers,... - [MCP 2.0: What Changes, What Breaks, and What You Need to Do About It](https://mlopstalks.com/talks/mcp-2-0-what-changes-what-breaks-and-what-you-need-to-do-about-it): Mateo Torres, Arcade.dev. Mateo Torres explains MCP 728 as the largest rewrite of the protocol since its launch. The central change is a move from stateful sessions to... - [MCP Release Overview: Stateless and the Big Changes in the New Spec](https://mlopstalks.com/talks/mcp-release-overview-stateless-and-the-big-changes-in-the-new-spec): Alex Hancock, Block. Alex Hancock explains the largest MCP protocol change since its launch. MCP started with local hosts and data sources, but more usage now happens between... - [MCPs for Observability Stacks](https://mlopstalks.com/talks/mcps-for-observability-stacks): Diana Todea, VictoriaMetrics. Diana Todea shows how Model Context Protocol can connect an AI assistant to an observability stack. Her examples combine a VictoriaMetrics cloud deployment with a... - [Responsible Autonomy: Building Governance Frameworks for AI That Act in the Real World via MCP](https://mlopstalks.com/talks/responsible-autonomy-building-governance-frameworks-for-ai-that-act-in-the-real): Saurabh Mishra, Optum. Saurabh Mishra explains how AI has moved from predictive models and chatbots toward agents that can reason, use tools, and perform actions in business systems.... - [Stateless, Yet Durable: MCP Tasks v2](https://mlopstalks.com/talks/stateless-yet-durable-mcp-tasks-v2): Cornelia Davis, Temporal. Cornelia Davis explains MCP Tasks v2 through a purchase order workflow that records received goods, updates inventory, closes the purchase order, and processes an invoice.... - [The MCP Tasks Extension](https://mlopstalks.com/talks/the-mcp-tasks-extension): Vikram Vaswani, Melonfire. Vikram Vaswani explains why synchronous Model Context Protocol requests are a poor fit for long-running work. Batch migrations, report generation, model training, and multi-step agent... - [What We Learned from Dozens of Enterprise MCP Deployments](https://mlopstalks.com/talks/what-we-learned-from-dozens-of-enterprise-mcp-deployments): Jiquan Ngiam, MintMCP. Jiquan Ngiam shares lessons from working with enterprise teams that deploy MCP and agents in production. He argues that the main problem has moved from... - [Events Notifications in MCP](https://mlopstalks.com/talks/events-notifications-in-mcp): Aman Singh, Microsoft. Aman Singh presents a design sketch for Events, a proposed Model Context Protocol extension. Current MCP notifications require an open connection and usually carry only... - [JSON Schema 2020-12 and the Contract for Context](https://mlopstalks.com/talks/json-schema-2020-12-and-the-contract-for-context): Ola Hungerford, Nordstrom. Ola Hungerford explains why MCP moved from a small JSON Schema subset to JSON Schema 2020-12 for tool schemas. The earlier limits caused SDKs and... - [Loop Engineering](https://mlopstalks.com/talks/loop-engineering): David DeStefano & Sam Christensen, EvolutionIQ & Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sparsh Jain, CentralAgent AI. This reading group discusses loop engineering rather than walking through a named paper or book. Sparsh Jain frames it as the next stage after prompt,... - [MCP Goes Stateless](https://mlopstalks.com/talks/mcp-goes-stateless): John Dellenbaugh, Early-stage AI startup & Pankaj Kumar, Amazon. John Dellenbaugh and Pankaj Kumar explain why the 2026-07-28 MCP specification changes horizontal scaling. Their shopping-cart demo first shows the old design, where an MCP... - [Policy Enforcement and Tamper-Evident Audit Chains](https://mlopstalks.com/talks/policy-enforcement-and-tamper-evident-audit-chains): Imran Siddique, Opaque Systems. Imran Siddique argues that MCP adoption has moved beyond basic agents and chatbots, while policy enforcement has become a practical requirement for production systems. Policy... - [Coding Agents Are Secretly General Agents](https://mlopstalks.com/talks/coding-agents-are-secretly-general-agents): Jay Hack, ClickUp. Jay Hack traces coding agents from early tools such as Kite and GitHub Copilot to Cursor and autonomous ticket-to-pull-request systems. He explains why code became... - [Sandboxing, Agent Harnesses, and Agent Teamwork](https://mlopstalks.com/talks/sandboxing-agent-harnesses-and-agent-teamwork): Shahram Anver, Cleric. Shahram Anver explains how Cleric changed its AI SRE architecture as models improved. The company moved from a complicated ant-colony design with many specialized workers... - [Omnigent: Composition, Control, and Collaboration for AI Agents](https://mlopstalks.com/talks/omnigent-composition-control-and-collaboration-for-ai-agents): Denny Lee, Databricks. Denny Lee describes Omnigent as an open-source layer above models and agent harnesses. He wants developers to keep their context, skills, memory, and configuration while... - [Logs Are All You Need: Rethinking Observability with AI Agents](https://mlopstalks.com/talks/logs-are-all-you-need-rethinking-observability-with-ai-agents): Sherwood Callaway, Sazabi. Sherwood Callaway describes Sazabi as an AI-native observability platform for teams that ship quickly. Its interface is chat, including a Slackbot, because engineers can ask... - [Autonomous Agents at Work: From OpenClaw Hype to Enterprise Reality](https://mlopstalks.com/talks/autonomous-agents-at-work-from-openclaw-hype-to-enterprise-reality): Pramod Krishnan, PwC. Pramod Krishnan explains why agents that take actions need stronger controls than systems that only answer questions. He classifies work as reversible, sensitive, or consequential,... - [Voice Agent Use Cases](https://mlopstalks.com/talks/voice-agent-use-cases): Anurag Beniwal, ElevenLabs. Anurag Beniwal describes the engineering choices behind production voice agents. He prefers architectures between simple cascaded pipelines and fully speech-to-speech systems because enterprises need control... - [Agents & the $40M Bet on Multiplayer AI](https://mlopstalks.com/talks/agents-the-40m-bet-on-multiplayer-ai): Stanislas Polu, Dust. Stanislas Polu describes the shift from single-player AI, where one person works privately with an agent, toward multiplayer AI for work that spans teams and... - [Context Engineering for Coding Agents](https://mlopstalks.com/talks/context-engineering-for-coding-agents): . Fausto presents coding agents as systems whose behaviour depends heavily on context injection. Engineers cannot directly control the model's internal parameters, but they can control... - [AI Is Fast. AI Projects Are Slow. Let's Fix That.](https://mlopstalks.com/talks/ai-is-fast-ai-projects-are-slow-lets-fix-that): JRocketRide's Joe Maionchi. Joe Maionchi and Rod Christensen describe RocketRide as an open-source framework for building AI pipelines from typed nodes connected by data lanes. Their argument is... - [Architecting Modern AI Systems](https://mlopstalks.com/talks/architecting-modern-ai-systems): . The panel discusses how AI platforms are changing as teams adopt agents, open-source models, and more distributed systems. Frederick describes a mental-health hackathon run with... - [Architecting Modern AI Systems: Platforms, Agents, and Integration](https://mlopstalks.com/talks/architecting-modern-ai-systems-platforms-agents-and-integration): Allen Roush, BuzzHPC & Frédéric Bénard, Mila & Shuo Wang, Bell Canada. The panel discusses how AI platforms are changing as teams adopt agents, open models, and more distributed systems. The hackathon example grounds the discussion: more... - [What's Special About Meta's Multi-Agent Systems](https://mlopstalks.com/talks/whats-special-about-metas-multi-agent-systems): Aditya Gautam, Meta. Aditya Gautam describes an application-layer multi-agent system for two short-form video problems: modality misalignment and original-content attribution. A video can contain a brief policy-breaking segment... - [Building MCP Before MCP Existed: Inside Despegar's Sofia Agent](https://mlopstalks.com/talks/building-mcp-before-mcp-existed-inside-despegars-sofia-agent): Nicolas Alejandro Bogliolo, Despegar. Nicolas Alejandro Bogliolo explains how Despegar built Sofia, its travel concierge, before LangChain and the Model Context Protocol were widely available. The system began with... - [The Latency Goldilocks Zone Explained](https://mlopstalks.com/talks/the-latency-goldilocks-zone-explained): Rafael Borger & Daniel Wolbert, iFood. Rafael Borger and Daniel Wolbert explain how iFood is building ILO, a conversational ordering experience for users with very different tastes, budgets, and habits. ILO... - [Building AI Agents That Survive Production](https://mlopstalks.com/talks/building-ai-agents-that-survive-production): Haytham Abuelfutuh, Union.ai. Haytham Abuelfutuh argues that production agents will fail, so teams should make those failures cheap to handle. He presents three design principles for an agent... - [Stop AI Agents From SQL Injecting Your Database](https://mlopstalks.com/talks/stop-ai-agents-from-sql-injecting-your-database): Averi Kitsch, Google. Averi Kitsch explains what Google has learned from more than 20 million monthly tool calls to Google Cloud databases. She describes three common database-tool patterns,... - [Why AI Agents Shouldn't Replace Your Fraud Models](https://mlopstalks.com/talks/why-ai-agents-shouldnt-replace-your-fraud-models): Varant Zanoyan, Zipline AI. Varant Zanoyan argues that agents should improve the models behind fraud detection, underwriting, search ranking, and other high-stakes systems instead of replacing those models at... - [The Creator of Superpowers: Why Real Agentic Engineering Beats Vibe Coding](https://mlopstalks.com/talks/the-creator-of-superpowers-why-real-agentic-engineering-beats-vibe-coding): Jesse Vincent, Prime Radiant. Jesse Vincent explains how Superpowers turns Claude Code into a more disciplined software development workflow. The process starts with brainstorming, where the agent helps the... - [Getting Humans Out of the Way: How to Work with Teams of Agents](https://mlopstalks.com/talks/getting-humans-out-of-the-way-how-to-work-with-teams-of-agents): Rob Ennals, Broomy. Rob Ennals describes a way to work with coding agents without becoming the reviewer for every line and interaction. His feature walk-through process has an... - [OpenXData Conference](https://mlopstalks.com/talks/openxdata-conference): Will Angel. OpenXData Conference 2026 covers how open data systems are changing as AI agents become major consumers of data. The keynote argues that lakehouses must evolve... - [It's 2026, and We're Still Talking Evals](https://mlopstalks.com/talks/its-2026-and-were-still-talking-evals): Maggie Konstanty, Prosus. Maggie Konstanty argues that evals should begin when a product idea begins and continue throughout development and production. Pre-ship tests can simulate personas and scenarios,... - [Why Agents are Driving Software Development to the Cloud](https://mlopstalks.com/talks/why-agents-are-driving-software-development-to-the-cloud): Zach Lloyd, Warp. Zach Lloyd argues that coding agents should move off individual laptops and into a shared cloud system. He compares agents to teammates or cloud functions,... - [A New Kind of Marketplace](https://mlopstalks.com/talks/a-new-kind-of-marketplace): Donné Stevenson, Prosus & Pedro Chaves, OLX Group. Donné Stevenson and Pedro Chaves discuss how agents could change buying and selling across real estate, automotive, and general classified marketplaces. Pedro describes a real-estate... - [How We Cut LLM Latency 70% With TensorRT in Production](https://mlopstalks.com/talks/how-we-cut-llm-latency-70-with-tensorrt-in-production): Maher Hanafi, Betterworks. Maher Hanafi describes how he moved from having no AI experience to leading self-hosted LLM infrastructure for an HR technology company. He explains the hidden... - [The Modern Software Engineer](https://mlopstalks.com/talks/the-modern-software-engineer): Mihail Eric, Monaco and Stanford University. Mihail Eric describes software engineering in a world where coding agents can write, test, and explain code. He argues that agents require more upfront thought... - [Fixing GPU Starvation in Large-Scale Distributed Training](https://mlopstalks.com/talks/fixing-gpu-starvation-in-large-scale-distributed-training): Kashish Mittal, Uber. Kashish Mittal describes GPU starvation as a data pipeline problem. Models can sit idle because training reads too much data, moves duplicated features between CPU... - [Ship Agents: A Virtual Conference Track 2](https://mlopstalks.com/talks/ship-agents-a-virtual-conference-track-2): Adam Boaz Becker & Sarmad Absil, Trial Cyber & Divia Mahajan, Amazon Alexa. Track 2 covers four production problems for agents. Sarmad Absil presents a manufacturing system that turns IoT anomalies into shared Microsoft Teams alerts, then uses... - [MCP Dev Summit [Day 2]](https://mlopstalks.com/talks/mcp-dev-summit-day-2): Jim Zemlin, Linux Foundation & Angie Jones, Linux Foundation and Agentic AI Foundation & Ido Salomon & Ryan Cook, WorkOS & Nick Cooper, OpenAI & Cecilia Lou, Docker & Ola Hungerford, Nordstrom & Jacob Wilson, PwC & Ana Musio, Bloomberg & Bob Dickinson, Team Spark & Harshit Kohli, Amazon Web Services & Jonathan Leitschuh, Braze & Carlos Santana, Amazon Web Services. Day 2 of MCP Dev Summit focused on how MCP is moving beyond simple tool calls. Ido Salomon and Lead Ysef presented MCP apps, which... - [The Coding Agent Multiverse of Madness](https://mlopstalks.com/talks/the-coding-agent-multiverse-of-madness): Ankit Mathur, Databricks. Ankit Mathur argues that enterprises are losing control as developers adopt Claude Code, Cursor, Codex, and other coding agents for different tasks. IT teams face... - [MCP Dev Summit [Day 1]](https://mlopstalks.com/talks/mcp-dev-summit-day-1): Shannon Williams, Obot AI & Jim Zemlin, Linux Foundation & David Soria Parra, Anthropic & David Nalley, AWS & James Hood, Amazon Web Services & Magna Sumasandra & Rash Tini, Uber & Sheng Liang, Obot AI & Aaron Wang, Duolingo & Adam Seligman & Zayn Turner, Workato & Diamond Bishop, Datadog & Nick Aldridge, Mousetrap & Alex Salazar, Arcade.dev & Jake Diamond Arivich, Jupyter & Kiierra Dodson, Further & Daniel Abdel Samid, Apollo & Juan Antonio Oz, Stacklok & Alharith Hussin, Alterion & Rick Nucci, Guru & Jonathan Rochelle, Lutely & Harshul Jain, Audible & Abhishek Khanna, Blueflame AI & Du'An Lightfoot, AWS & Lin Sun, Solo.io & Saurabh Yergattikar, eBay & Sanjay Vakil, DirectBooker & Jonathan Freeland, Shashank Khanna & Hillary Curran & Cecilia Liu, Docker & Diamond Bishop, Datadog & Paul Carleton, Anthropic. Day 1 presents MCP as an integration layer that is moving from rapid adoption into enterprise production. David Soria Parra describes the protocol's growth from... - [2026 The Year of Agent Orchestration](https://mlopstalks.com/talks/2026-the-year-of-agent-orchestration): Zach Lloyd, Warp. Zach Lloyd argues that coding has shifted from writing code by hand to writing prompts and guiding agents. As engineers run several agents at once,... - [Decomposing the Agent Orchestration System: Lessons Learned](https://mlopstalks.com/talks/decomposing-the-agent-orchestration-system-lessons-learned): Niels Bantilan, Union.ai. Niels Bantilan explains what Union learned while building Flyte 2.0 and productionizing agentic systems. His concern is the infrastructure around an agent, especially failures caused... - [How to Make a Coding Agent a General Purpose Agent](https://mlopstalks.com/talks/how-to-make-a-coding-agent-a-general-purpose-agent): Harrison Chase, LangChain & Sam Partee, Arcade. Harrison Chase and Sam Partee divide a general purpose agent into two layers. The agent harness gives a model a coding-agent experience through file tools,... - [Stop Shipping on Vibes: How to Build Real Evals for Coding Agents](https://mlopstalks.com/talks/stop-shipping-on-vibes-how-to-build-real-evals-for-coding-agents): Jessica Wang, Braintrust. Jessica Wang argues that teams often ship AI features because a PM tried a few prompts or an engineer declared the feature ready. She proposes... - [Everything We Got Wrong About Research-Plan-Implement](https://mlopstalks.com/talks/everything-we-got-wrong-about-research-plan-implement): Dexter Horthy, HumanLayer. Dexter Horthy revisits the Research-Plan-Implement workflow after seeing experts get good results while their teams struggled. Research often became opinionated because agents were told what... - [Lessons from 25 Trillion Tokens: Scaling AI-Assisted Development at Kilo](https://mlopstalks.com/talks/lessons-from-25-trillion-tokens-scaling-ai-assisted-development-at-kilo): Scott Breitenother, Kilo. Scott Breitenother describes how Kilo changed its engineering model after processing 25 trillion tokens and serving more than 1.5 million developers. The company has about... - [Performance Optimization and Software/Hardware Co-design across PyTorch, CUDA, and NVIDIA GPUs](https://mlopstalks.com/talks/performance-optimization-and-software-hardware-co-design-across-pytorch-cuda): Chris Fregly, AI performance engineer, startup founder, and investor. Chris Fregly discusses the ideas behind his O'Reilly book AI Systems Performance Engineering and the GitHub material that accompanies it. He explains why hardware, software,... - [Write Reliable Software with Temporal](https://mlopstalks.com/talks/write-reliable-software-with-temporal): Johann Schleier-Smith, Temporal. Johann Schleier-Smith describes durable execution as a programming model that makes software crash-proof. Temporal stores workflow state and activity results so a program can replay... - [Using Agents in Production: Past Present and Future](https://mlopstalks.com/talks/using-agents-in-production-past-present-and-future): Euro Beinat, Prosus. Euro Beinat describes how Prosus is deploying agents across its e-commerce businesses and internal workforce. The company expects 30,000 agents in production by the end... - [Context Engineering 2.0: MCP, Agentic RAG & Memory](https://mlopstalks.com/talks/context-engineering-2-0-mcp-agentic-rag-memory): Simba Khadder, Redis. Simba Khadder argues that agents need one unified context surface instead of separate systems for RAG, memory, and structured data. RAG works well for documents,... - [Enterprise-ready MCP](https://mlopstalks.com/talks/enterprise-ready-mcp): Jiquan Ngiam, MintMCP. Jiquan Ngiam describes the move from software written line by line to agents that interpret instructions, choose tools, and work toward goals. This gives business... - [From Chat Fatigue to Instant Action](https://mlopstalks.com/talks/from-chat-fatigue-to-instant-action): Donné Stevenson, Prosus. Donné Stevenson describes building an agent for car dealers on Autooto, a Polish secondhand-car marketplace. The aim was to help dealers understand their listings and... - [Open vs Closed Source Agent Infra?](https://mlopstalks.com/talks/open-vs-closed-source-agent-infra): Adel El Hallak, NVIDIA. This panel discusses how teams should choose between open and closed agent infrastructure. Laurel recommends experimenting with several open-source frameworks to learn where agents succeed... - [A Playground for AI Engineers](https://mlopstalks.com/talks/a-playground-for-ai-engineers): Paulo Vasconcellos, Hotmart. Paulo Vasconcellos describes Hotmart as a broad testing ground for applied AI. The company uses machine learning for fraud, content moderation, recommendations, forecasting, ticket classification,... - [Dynamic Contextual Retrieval in Enterprise Analytics](https://mlopstalks.com/talks/dynamic-contextual-retrieval-in-enterprise-analytics): Dirk Petzoldt, explai.com. Dirk Petzoldt argues that enterprise analytics requires context engineering rather than ever larger prompts. An analyst does more than write SQL: the work involves forming... - [Multi-Agent Personalization with Shared Memory: From Email to Website to Proposal](https://mlopstalks.com/talks/multi-agent-personalization-with-shared-memory-from-email-to-website-to-proposal): Hamed Taheri, Personize.ai. Hamed Taheri describes Personize.ai's work on personalization for companies with large customer databases. The system uses multiple agents to research customers, infer missing attributes, plan... - [Cracking the Black Box: Real-Time Neuron Monitoring & Causality Traces](https://mlopstalks.com/talks/cracking-the-black-box-real-time-neuron-monitoring-causality-traces): Mike Oaten, TIKOS. Mike Oaten explains how AI teams can turn the EU AI Act from a legal concern into an engineering plan. He focuses on the harmonized... - [MLflow Leading Open Source](https://mlopstalks.com/talks/mlflow-leading-open-source): Databricks' Corey Zumar. Corey Zumar, Jules Damji, and Danny Chiao describe how MLflow is adapting to production GenAI applications. They say most current use cases remain chatbots, but... - [Simulate to Scale: How realistic simulations power reliable agents in production](https://mlopstalks.com/talks/simulate-to-scale-how-realistic-simulations-power-reliable-agents-in-production): Sachi Shah, Sierra. Sachi Shah explains how Sierra tests customer-facing agents before they interact with real users. Traditional unit, integration, and smoke tests still help, but agents are... - [Yes, we do need MCP](https://mlopstalks.com/talks/yes-we-do-need-mcp): Ben Hindman, reboot.dev. Ben Hindman argues that statefulness, usually treated as a liability in distributed systems, is necessary for useful AI applications. Chat-based systems need context from other... - [Agents as Search Engineers](https://mlopstalks.com/talks/agents-as-search-engineers): Santoshkalyan Rayadhurgam, Meta. Santoshkalyan Rayadhurgam argues that search systems must account for users expressing partial intent instead of complete, well-formed queries. Examples such as finding a Python memory... - [Building an Orchestration Layer for Agentic Commerce at Loblaws](https://mlopstalks.com/talks/building-an-orchestration-layer-for-agentic-commerce-at-loblaws): Mefta Sadat, Loblaw Digital. Mefta Sadat explains how Loblaw Digital built Alfred, a reusable orchestration layer for agentic applications. The system sits between front-end applications and Loblaw's platform APIs,... - [Time to become a hacker](https://mlopstalks.com/talks/time-to-become-a-hacker): Matt Sharp, Flexion. Matt Sharp argues that coding agents have made attacks easier because they reduce the skill and effort needed to exploit software. Prompt injection is his... - [How AI covered a human's paternity leave](https://mlopstalks.com/talks/how-ai-covered-a-humans-paternity-leave): Quinten Rosseel, Wobby. Quinten Rosseel describes how Wobby deployed AI analysts for business teams and learned what made the system useful in daily work. The team moved from... - [When Agents Learn to Feel: Multi-Modal Affective Computing in Production](https://mlopstalks.com/talks/when-agents-learn-to-feel-multi-modal-affective-computing-in-production): Chenyu Zhang, GlowingStar. Chenyu Zhang argues that AI agents need to respond to a user's emotional state as well as the user's words. He proposes adding a multimodal... - [MCP Security: The Exploit Playbook (And How to Stop Them)](https://mlopstalks.com/talks/mcp-security-the-exploit-playbook-and-how-to-stop-them): . Vitor explains how MCP servers expand an agent's access to data, tools, and external systems while security controls remain immature. He focuses on prompt injection,... - [The Future of Coding: AI Agents & the Next Tech Revolution](https://mlopstalks.com/talks/the-future-of-coding-ai-agents-the-next-tech-revolution): Ricky Doar, Cursor. Ricky Doar describes the habits he sees among effective AI coding teams working with Cursor. The main skill is learning how to divide work into... - [Building Artificial Engineering Intelligence for Engineering Teams](https://mlopstalks.com/talks/building-artificial-engineering-intelligence-for-engineering-teams): Aishwarya Shankar, Intelligence AI. Aishwarya Shankar describes Intelligence AI's approach to making coding agents useful for whole engineering organizations. The system works at several levels: background agents handle tasks... - [Beyond the Gold Standard: Evaluating and Trusting Agents in the Wild](https://mlopstalks.com/talks/beyond-the-gold-standard-evaluating-and-trusting-agents-in-the-wild): Sanjana Sharma, Prosus. Sanjana Sharma argues that model benchmarks do not predict whether an agent will work in production. Real workflows contain ambiguous requirements, conflicting records, missing fields,... - [Fast & Asynchronous: Drift Your AI, Not Your GPU Bill](https://mlopstalks.com/talks/fast-asynchronous-drift-your-ai-not-your-gpu-bill): Artem Yushkovskiy, Delivery Hero. Artem Yushkovskiy describes how Delivery Hero processes restaurant images with AI. The original system used Kubeflow pipelines that called external APIs, but scaling to hundreds... - [Rethinking Notebooks Powered by AI](https://mlopstalks.com/talks/rethinking-notebooks-powered-by-ai): Vincent Warmerdam, marimo. Vincent Warmerdam explains why he thinks notebooks need to become more like interactive programs and less like static scratchpads. marimo keeps notebooks as Python files,... - [Tool Calling](https://mlopstalks.com/talks/tool-calling): Alex Salazar, Arcade.dev & Nishikant Dhanuka, Prosus Group & Luciana Ledesma, MeaningStack. The panel examines what tool calling requires when agents move beyond demos. Alex Salazar describes three tool layers: low-level service tools, organization-specific workflows, and agent-specific... - [The Shadow AI Problem Nobody's Talking About](https://mlopstalks.com/talks/the-shadow-ai-problem-nobodys-talking-about): Euro Beinat, Prosus Group. Euro Beinat argues that AI adoption is an organizational change problem as much as a technology problem. CTOs now need to help every department understand... - [Speed and Scale: How Today's AI Datacenters Are Operating Through Hypergrowth](https://mlopstalks.com/talks/speed-and-scale-how-todays-ai-datacenters-are-operating-through-hypergrowth): Kris Beevers, NetBox Labs. Kris Beevers describes AI infrastructure as a rapidly expanding industry with severe constraints at every stage. Power, cooling, land, GPUs, networking equipment, cabling, procurement, and... - [Real-time features, AI search, Agentic similarities](https://mlopstalks.com/talks/real-time-features-ai-search-agentic-similarities): Varant Zanoyan & Nikhil Simha Raprolu, Zipline AI. Varant Zanoyan and Nikhil Simha Raprolu explain why Zipline AI is building around Chronon, an open-source system that grew from Airbnb's fraud and search problems... - [Why Emotion Matters More Than Sound](https://mlopstalks.com/talks/why-emotion-matters-more-than-sound): Anoop Dawar, Deepgram & Ajeet Grewal, Sierra. Anoop Dawar and Ajeet Grewal explain why production voice agents require much more than a language model connected to speech APIs. Voice systems must handle... - [Stop Building AI Like Traditional Software](https://mlopstalks.com/talks/stop-building-ai-like-traditional-software): Aishwarya Naresh Reganti, LevelUp Labs. Aishwarya Naresh Reganti argues that teams should stop treating generative AI as a normal software feature. Traditional software has a defined interface and predictable user... - [The Semantic Layer and AI Agents](https://mlopstalks.com/talks/the-semantic-layer-and-ai-agents): David Jayatillake, Cube.dev. David Jayatillake argues that semantic layers are already present in every company. The question is whether business definitions live in a person's head or are... - [Co-Engineering: The New Era of Human-AI Collaboration](https://mlopstalks.com/talks/co-engineering-the-new-era-of-human-ai-collaboration): Kiriti Badam, OpenAI. Kiriti Badam describes co-engineering as a way to use coding agents in enterprise software development. He compares agents with junior engineers who need clear requirements,... - [Coding with AI](https://mlopstalks.com/talks/coding-with-ai): Chip Huyen, Tep Studio. Chip Huyen describes how AI coding tools are changing software work. She compares IDE assistants, terminal agents, GitHub-based workflows, and web interfaces, then proposes measuring... - [Context Engineering pitfalls for our e-commerce agent](https://mlopstalks.com/talks/context-engineering-pitfalls-for-our-e-commerce-agent): Nishikant Dhanuka & Chiara Carateli, Prosus. Nishikant Dhanuka and Chiara Carateli describe how iFood built Ailo, a conversational agent for food ordering in Brazil. The agent runs in the iFood app... - [Expanding context engineering to the tooling layer](https://mlopstalks.com/talks/expanding-context-engineering-to-the-tooling-layer): Frank Wittkampf, Databook. Frank Wittkampf argues that prompt engineering must include the tools an agent can see and the way those tools are described. MCP standardizes connections to... - [Feedback Loops for Agentic Workflows](https://mlopstalks.com/talks/feedback-loops-for-agentic-workflows): . Tudor explains feedback loops through examples from BTO, where users built workflows with as many as hundreds of manually connected nodes. A good loop sends... - [From Notebooks to Production FASTER](https://mlopstalks.com/talks/from-notebooks-to-production-faster): Shahd Alghrsi, Virgin Media. Shahd Alghrsi describes how Virgin Media built an MLOps platform that helps data scientists move from experiments to production. The platform uses customizable container images,... - [Graph Neural Networks Just Solved Enterprise AI?](https://mlopstalks.com/talks/graph-neural-networks-just-solved-enterprise-ai): Jure Leskovec, Stanford University and Kumo.AI. Jure Leskovec argues that enterprise AI has overlooked its most valuable data: structured records and the relationships between them. Traditional predictive models usually join tables,... - [What if AI Doesn't Need Structure, It Needs Connection?](https://mlopstalks.com/talks/what-if-ai-doesnt-need-structure-it-needs-connection): David Vargas Fuertes, Vellum. David Vargas Fuertes argues that AI systems often force language models to communicate in JSON even though models are trained on much more natural language,... - [MCP Security: What Happens When Your Agents Talk to Everything?](https://mlopstalks.com/talks/mcp-security-what-happens-when-your-agents-talk-to-everything): . Rosemary explains MCP as a universal adapter that lets AI applications connect to databases, Slack, GitHub, file systems, and internal APIs. The security problem is... - [Multi-Agent Systems for the Misinformation Lifecycle](https://mlopstalks.com/talks/multi-agent-systems-for-the-misinformation-lifecycle): . Aditya presents a five-agent architecture for automating parts of professional fact-checking. The system classifies misinformation, indexes trusted sources, retrieves and reranks relevant evidence, reasons about... - [Real-Time Voice Agents in Production](https://mlopstalks.com/talks/real-time-voice-agents-in-production): Panos Stravopodis, Elyos AI. Panos Stravopodis explains how Elyos AI builds voice agents for home-services companies. The agents connect to customer CRM and ERP systems and handle calls, messages,... - [Structured Dissent Patterns for Agentic Production Reliability](https://mlopstalks.com/talks/structured-dissent-patterns-for-agentic-production-reliability): Phil Stafford, MLOps Community. Phil Stafford presents structured dissent, a multi-agent pattern for decisions where there is no simple ground truth. A default swarm uses two believer agents, two... - [Inside OpenAI's AI Agent Collaboration System](https://mlopstalks.com/talks/inside-openais-ai-agent-collaboration-system): . Robert explains how OpenAI evaluates collaborative agents with graders. He contrasts structured evals with judging models by personal impressions, then describes a progression from vibes-based... - [Tool definitions are the new Prompt Engineering](https://mlopstalks.com/talks/tool-definitions-are-the-new-prompt-engineering): Chiara Caratelli, Prosus Group & Alex Salazar, Arcade.dev. Chiara Caratelli describes an AI food-ordering agent built for iFood, where users can search, refine, and order through the app or WhatsApp. The team found... - [Accelerating Growth Through Optimizing GPU Usage](https://mlopstalks.com/talks/accelerating-growth-through-optimizing-gpu-usage): Sahil Khanna, Adobe. Sahil Khanna describes how Adobe built a compute platform for Firefly's generative AI workloads. The platform supports hundreds of distributed jobs and thousands of GPU... - [Enterprise AI Operations: The Missing Piece](https://mlopstalks.com/talks/enterprise-ai-operations-the-missing-piece): Rani Radhakrishnan, PwC US. Rani Radhakrishnan describes managed services as the support work that begins when software reaches production. At PwC, her team applies automation and AI to that... - [Building Agentic Tools for Production](https://mlopstalks.com/talks/building-agentic-tools-for-production): Sam Partee, Arcade AI. Sam Partee explains that production agentic systems depend on the design and testing of individual tools, rather than only on evaluating the agent as a... - [AI REWIND 2025 - MLOps Reading Group Year-end Special](https://mlopstalks.com/talks/ai-rewind-2025-mlops-reading-group-year-end-special): Sophia Skowronski, Breckinridge Capital Advisors & Adam Becker, MLOps Community & Rohan Prasad, EvolutionIQ & Nehil Jain, Stealth AI Startup & Sonam Gupta, AI Camp & Lucas Pavanelli, Stone. This reading-group year-end special does not cover a single paper. It reviews the community's most consequential AI developments from 2025, including production agents, context engineering,... - [The Future of AI Agents are Sandboxes](https://mlopstalks.com/talks/the-future-of-ai-agents-are-sandboxes): Jonathan Wall, Runloop.ai. Jonathan Wall argues that the main infrastructure problem for AI agents is giving them a safe computer to use. A sandbox isolates an agent's files,... - [Big Updates to Redis: Context Engine, Tools, and Memory](https://mlopstalks.com/talks/big-updates-to-redis-context-engine-tools-and-memory): Simba Khadder, Redis. Simba Khadder describes Redis's move from caching, rate limiting, and session storage toward providing real-time context for agents. He separates context into unstructured data, structured... - [Context Engineering 2.0](https://mlopstalks.com/talks/context-engineering-2-0): Simba Khadder, Redis. Simba Khadder explains why he does not see feature stores as obsolete after Featureform joined Redis. MLOps has worked best where model quality has a... - [Does AgenticRAG Really Work?](https://mlopstalks.com/talks/does-agenticrag-really-work): Satish Bhambri, Walmart Labs. Satish Bhambri explains how RAG evolved into agentic RAG systems that use specialized agents for specific data sources and business tasks. A conventional language model... - [How Sierra AI Does Context Engineering](https://mlopstalks.com/talks/how-sierra-ai-does-context-engineering): Zack Reneau-Wedeen, Sierra. Zack Reneau-Wedeen explains why AI agents need different development methods from traditional software. Sierra runs conversations repeatedly, checks them against task-specific criteria, and uses evaluator... - [Governance for AI Agent Deployment](https://mlopstalks.com/talks/governance-for-ai-agent-deployment): Spencer Reagan, Airia. Spencer Reagan describes where AI agents are producing practical value and where deployment becomes difficult. He points to spreadsheet-heavy work, customer-profile creation, summarization, document review,... - [Voice AI's Biggest Weakness Exposed](https://mlopstalks.com/talks/voice-ais-biggest-weakness-exposed): Brooke Hopkins, Coval. Brooke Hopkins explains why voice AI is spreading beyond experiments and into customer support, healthcare, logistics, field work, and documentation. Its appeal comes from being... - [Linear's Approach to Production AI Agents](https://mlopstalks.com/talks/linears-approach-to-production-ai-agents): Kristin Boyer, LINEAR. Kristin Boyer describes how LINEAR experiments with AI features and focuses on a Slack-integrated Linear agent. The agent lets users ask questions about their workspace... - [MCP-Enabled Agents](https://mlopstalks.com/talks/mcp-enabled-agents): Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sophia Skowronski, Breckinridge Capital Advisors & Arthur Coleman, Online Matters & Tamese Salai. This reading-group session discusses the LiveMCP-101 benchmark for testing agents that use the Model Context Protocol. The benchmark contains 101 tasks built from 41 MCP... - [Sub-Agent Architectures: What You Can Leverage](https://mlopstalks.com/talks/sub-agent-architectures-what-you-can-leverage): Sidd Seethepalli, Vellum. Sidd Seethepalli explains why Vellum moved from a drag-and-drop agent editor to a natural language agent builder. He shares practical lessons from building and testing... - [The Vector Search Engine Powering AI Agents](https://mlopstalks.com/talks/the-vector-search-engine-powering-ai-agents): Thierry Damiba, Qdrant. Thierry Damiba explains why vector search is useful inside AI agents. Agents need to remember past interactions, search across separate enterprise data sources, and handle... - [The Next Evolution of AI Agents](https://mlopstalks.com/talks/the-next-evolution-of-ai-agents): Alon Horev, Vast Data. Alon Horev describes Vast Data's operating system for AI, which combines storage, a database, data movement across locations, and compute services. He explains why large... - [The Real Reason Your AI Models Forget](https://mlopstalks.com/talks/the-real-reason-your-ai-models-forget): Jeff Huber, Chroma. Jeff Huber and Demetrios Brinkmann discuss why AI systems lose track of useful information. Huber describes tests across more than 17 models that found attention... - [AI Agents Are About to Get Real, Here's Why It Matters](https://mlopstalks.com/talks/ai-agents-are-about-to-get-real-heres-why-it-matters): Sam Partee, Arcade AI. Sam Partee argues that agent development has moved from collecting context to taking actions in external systems. Function calling and structured outputs made tool use... - [Meta-Prompting: The Hack That's Changing Production AI](https://mlopstalks.com/talks/meta-prompting-the-hack-thats-changing-production-ai): Aman Khan, Arize. Aman Khan explains how system prompts can be optimized after an agent is deployed. He compares traditional reinforcement learning, which optimizes a numeric reward, with... - [The Latency Problem Nobody Talks About](https://mlopstalks.com/talks/the-latency-problem-nobody-talks-about): Anoop Dawar, Deepgram. Anoop Dawar explains how voice AI moved from batch transcription toward live systems that combine speech recognition, language-model reasoning, and speech generation. He argues that... - [The GPU Uptime Battle](https://mlopstalks.com/talks/the-gpu-uptime-battle): Andy Pernsteiner, VAST Data. Andy Pernsteiner explains why AI systems become difficult when they move beyond a laptop or a few servers. More data brings more variety, and larger... - [Big updates to MLflow 3.0](https://mlopstalks.com/talks/big-updates-to-mlflow-3-0): Eric Peter & Corey Zumar, Databricks. Eric Peter and Corey Zumar explain how MLflow applies an engineering lifecycle to generative AI applications. Eric starts with tracing, which captures the steps inside... - [The Claude Code Story: How Two Guys Changed AI Forever](https://mlopstalks.com/talks/the-claude-code-story-how-two-guys-changed-ai-forever): Siddharth Bidasaria, Anthropic. Siddharth Bidasaria describes Claude Code's path from a terminal experiment inside Anthropic's labs team to a product that quickly attracted internal and external users. The... - [Fine-Tuned Models Are Getting Out of Hand](https://mlopstalks.com/talks/fine-tuned-models-are-getting-out-of-hand): Jaipal Singh Goud, Prem AI. Jaipal Singh Goud distinguishes between fast data and slow data. RAG can retrieve changing factual information, while fine-tuned models can learn the reasoning and preferences... - [Fine-Tuning is Broken](https://mlopstalks.com/talks/fine-tuning-is-broken): Tanmay Chopra, Neeva. Tanmay Chopra argues that most current fine-tuning is mislabeled extended pretraining. These systems keep next-token loss and the full language-model output head, so they mainly... - [Machine Consciousness? Get Real!](https://mlopstalks.com/talks/machine-consciousness-get-real): Ron Chrisley, University of Sussex. Ron Chrisley rejects both claims that machine consciousness already exists and that it is impossible. He examines the argument that language models understand because they... - [Synthetic Data for Industrial Computer Vision](https://mlopstalks.com/talks/synthetic-data-for-industrial-computer-vision): Vasu Sharma, Meta & Kasum Wani, Advex. Vasu Sharma and Kasum Wani describe synthetic data as a way to reduce the time needed to build industrial computer vision systems. Sharma explains that... - [Overcoming Agentic Memory Management Challenges](https://mlopstalks.com/talks/overcoming-agentic-memory-management-challenges): Biswaroop Bhattacharjee, Prem AI. Biswaroop Bhattacharjee explains how he built Cortex after studying agentic memory systems and human memory. The design stores summaries, keywords, tags, and relationships between memories... - [How to build agents that take ACTION](https://mlopstalks.com/talks/how-to-build-agents-that-take-action): Alex Salazar, Arcade. Alex Salazar argues that an AI system is not really an agent if it cannot take action. Chat can retrieve information, but useful software automates... - [Evals Aren't Useful? Really?](https://mlopstalks.com/talks/evals-arent-useful-really): Chiara Caratelli, Prosus Group. Chiara Caratelli explains that agents need evaluation because quick prototypes often fail when exposed to many users and unfamiliar conversations. Her process begins with curated... - [Building Data Centers for GPU Clouds](https://mlopstalks.com/talks/building-data-centers-for-gpu-clouds): Craig Tavares, Buzz HPC. Craig Tavares describes the infrastructure behind Buzz HPC's GPU cloud, drawing on experience with telecom networks, data centers, power plants, and cloud platforms. He explains... - [Beyond Chatbots: How to build Agentic AI systems with Google Gemini](https://mlopstalks.com/talks/beyond-chatbots-how-to-build-agentic-ai-systems-with-google-gemini): Philipp Schmid, Google DeepMind. Philipp Schmid explains how AI systems have moved from text completion and instruction following toward agents that can reason, call tools, and work through multi-step... - [How to Build Execution Layers That Don't Burn Out](https://mlopstalks.com/talks/how-to-build-execution-layers-that-dont-burn-out): Tanmay Tiwari. Tanmay Tiwari describes an execution layer for agentic systems that can keep working without constant supervision. He argues that systems often fail after the initial... - [Quantized LLM Training at Scale with ZeRO++](https://mlopstalks.com/talks/quantized-llm-training-at-scale-with-zero): Guanhua Wang, Microsoft. Guanhua Wang explains that communication becomes a major cost when large language models use many GPUs, especially with small micro-batches or limited inter-node bandwidth. ZeRO... - [Underwriting Assist: A Multi-Agent System](https://mlopstalks.com/talks/underwriting-assist-a-multi-agent-system): Somya Rai, EXL. Somya Rai describes Underwriting Assist, a multi-agent system for commercial insurance submissions. It reads emails and attachments, extracts information from documents and images, checks for... - [Why You Should Care About Observability in LLM Workflows](https://mlopstalks.com/talks/why-you-should-care-about-observability-in-llm-workflows): Colin McNamera, AlwaysCool.ai. Colin McNamera describes how AlwaysCool.ai introduced AI into food product formulation, nutrition analysis, label generation, and FDA compliance work. The team began with spreadsheets, ChatGPT,... - [Evaluating AI Agents: Why It Matters and How We Do It](https://mlopstalks.com/talks/evaluating-ai-agents-why-it-matters-and-how-we-do-it): Annie Condon & Jeff Groom, Acre Security. Annie Condon and Jeff Groom explain how Acre Security evaluates AI agents used in physical access control. They describe agents as software systems with non-deterministic... - [How to Optimize AI Agents in Production](https://mlopstalks.com/talks/how-to-optimize-ai-agents-in-production): . Nimrod argues that improving an AI agent in production is usually handled through biased, manual trial and error. Engineers change a prompt or model after... - [What It Takes to Run Multi-Agent Systems](https://mlopstalks.com/talks/what-it-takes-to-run-multi-agent-systems): Dipanwita Mallick, HP. Dipanwita Mallick describes the infrastructure problems enterprises face when moving from AI prototypes to production. Multi-agent workflows can use millions of tokens in a session,... - [An AI Company By Accident](https://mlopstalks.com/talks/an-ai-company-by-accident): Russ d'Sa, LiveKit. Russ d'Sa explains how LiveKit started in 2020 as an open-source answer to the difficulty of building real-time audio and video applications. Companies including Spotify,... - [Building Agents for Healthcare](https://mlopstalks.com/talks/building-agents-for-healthcare): Lars Maaløe, Corti. Lars Maaløe describes Corti's approach to building AI agents for healthcare. He starts with the pressure on clinicians, including growing patient volumes, more complex treatments,... - [Designing AI Agents for the Complex Realities of Healthcare](https://mlopstalks.com/talks/designing-ai-agents-for-the-complex-realities-of-healthcare): Dr. Sarah Gebauer, Validara Health. Dr. Sarah Gebauer compares AI agents in healthcare with medical residents. Residents make decisions with partial training, supervision, and a duty to ask for help.... - [The Cost of AI: FinOps Strategies for Intelligent Agents](https://mlopstalks.com/talks/the-cost-of-ai-finops-strategies-for-intelligent-agents): Advait Patel, Broadcom. Advait Patel explains how autonomous AI agents can quietly increase cloud spending. An agent may retry forever, reload full context on every step, retain logs... - [Beyond Prompting: The Emerging Discipline of Context Engineering Reading Group](https://mlopstalks.com/talks/beyond-prompting-the-emerging-discipline-of-context-engineering-reading-group): Adam Becker, HeadOn & Matt Squire, Fuzzy Labs & Rohan Prasad, EvolutionIQ. A Survey of Context Engineering for Large Language Models is the paper discussed in this reading group. Adam Becker presents the paper's framework, which treats... - [AI Needs Memory: Here's How It Works](https://mlopstalks.com/talks/ai-needs-memory-heres-how-it-works): Ben Labashian, Workhelix. Ben Labashian argues that memory is one of the hardest parts of building reliable AI agents. Calling memory simply "data" makes storage and retrieval easier... - [Building Advanced Agents Over Complex Data](https://mlopstalks.com/talks/building-advanced-agents-over-complex-data): Jerry Liu, LlamaIndex. Jerry Liu argues that data quality is a necessary part of production LLM applications. Basic RAG is easy to prototype with document splitting, dense retrieval,... - [Building Multi-Player AI Systems (and why it's SO hard)](https://mlopstalks.com/talks/building-multi-player-ai-systems-and-why-its-so-hard): Tula Masterman, MeshAgent. Tula Masterman argues that most agent systems stop at one person working with one agent or with a team of agents. Real business work involves... - [Is Open Source Software Actually Secure?](https://mlopstalks.com/talks/is-open-source-software-actually-secure): Hudson Buzby, JFrog. Hudson Buzby describes the gap between fast-moving AI development and the controls expected in enterprise software. Data science teams often worked outside standard DevOps practices,... - [Before Building AI Agents Watch These Hard Earned Lessons](https://mlopstalks.com/talks/before-building-ai-agents-watch-these-hard-earned-lessons): Nishikant Dhanuka, Prosus Group. Nishikant Dhanuka describes lessons from building productivity and e-commerce agents at Prosus Group. He argues that context engineering is usually more important than prompt tweaks... - [Catastrophic agent failure and how to avoid it](https://mlopstalks.com/talks/catastrophic-agent-failure-and-how-to-avoid-it): Edward Upton, Asteroid. Edward Upton describes failures from Asteroid's work on browser agents for healthcare, insurance, and fraud intelligence. He argues that an agent becomes dangerous when it... - [Zero Trust for Multi-Agent Systems](https://mlopstalks.com/talks/zero-trust-for-multi-agent-systems): Surendra Narang, Palo Alto Networks. Surendra Narang and Venkata Gopi Kolla explain how zero-trust security can be applied to multi-agent systems. They describe an architecture with an orchestrator, autonomous agents,... - [Advancing the Cost-Quality Frontier in Agentic AI](https://mlopstalks.com/talks/advancing-the-cost-quality-frontier-in-agentic-ai): Krista Opsahl-Ong, Databricks. Krista Opsahl-Ong describes how enterprises are using agents for document understanding, knowledge assistance, custom language model tasks, and chained workflows. She focuses on the work... - [Cutting Costs with Artificial Intelligence](https://mlopstalks.com/talks/cutting-costs-with-artificial-intelligence): . Rashad explains why multi-agent systems are harder to cost than single-agent applications. A run may include several model calls, hidden calls caused by natural-language communication,... - [Small Language Models are the Future of Agentic AI](https://mlopstalks.com/talks/small-language-models-are-the-future-of-agentic-ai): Adam Becker, MLOps Community & Nehil Jain, Stealth AI Startup & Sonam Gupta, AI Camp. The paper discussed is "Small Language Models are the Future of Agentic AI." Sonam Gupta introduced the paper's definitions of small language models and described... - [The Era of AI Agents in Marketing](https://mlopstalks.com/talks/the-era-of-ai-agents-in-marketing): Joel Horwitz, Neoteric3D. Joel Horwitz describes marketing as an early but fast-moving use case for AI agents. His team uses Clay and related workflows to detect signals such... - [The Future of Compute: How AI Agents Are Reshaping Infrastructure](https://mlopstalks.com/talks/the-future-of-compute-how-ai-agents-are-reshaping-infrastructure): Diego Oppenheimer, Guardrails AI. Diego Oppenheimer argues that AI agents are exposing a mismatch between traditional infrastructure and software that can perceive, reason, act, and remember. Conventional systems assume... - [A Deep Discussion with the Author of "Context Rot"](https://mlopstalks.com/talks/a-deep-discussion-with-the-author-of-context-rot): Kelly Hong, Chroma & Bauke Brenninkmeijer, orq.ai & Matt Squire, Fuzzy Labs & Arthur Coleman, Online Matters. Kelly Hong presents Context Rot, a Chroma technical report about how LLM performance changes as input length grows. She argues that million-token context windows do... - [Building Real-Time, Reliable Voice AI: From Simulation to Production](https://mlopstalks.com/talks/building-real-time-reliable-voice-ai-from-simulation-to-production): Brooke Hopkins, Coval. Brooke Hopkins and Peter Bakkum compare cascading voice systems with speech-to-speech systems and explain where each fits. Speech-to-speech provides native audio input and output, lower... - [How to Self-Host an AI Agent](https://mlopstalks.com/talks/how-to-self-host-an-ai-agent): . Meryem explains why AI agents create different infrastructure demands from simple chatbot inference. A low-agency system sends a prompt and returns an answer, while a... - [If There's Free Compute, There's Abuse: Fighting Fraud with Lightweight LLM Agents](https://mlopstalks.com/talks/if-theres-free-compute-theres-abuse-fighting-fraud-with-lightweight-llm-agents): Jonas Scholz, Sliplane. Jonas Scholz explains how Sliplane investigates abuse on its container hosting platform. Free trials attract crypto miners, VPN operators, scanners, DDoS activity, spam bots, and... - [Smart Agents Start with Smart LLM Choices](https://mlopstalks.com/talks/smart-agents-start-with-smart-llm-choices): Shai Rubin, Studel AI. Shai Rubin presents a practical way to choose an LLM for code understanding. He starts by defining the task and the measures that matter: concise... - [The Future of User Interfaces: AI is Changing Everything](https://mlopstalks.com/talks/the-future-of-user-interfaces-ai-is-changing-everything): . The talk introduces Machine Experience, or MX, engineering as the design of interfaces for AI models. The speaker uses a Slack DM example to show... - [Distilling 200+ Hours of NeurIPS: What's Next for AI](https://mlopstalks.com/talks/distilling-200-hours-of-neurips-whats-next-for-ai): Nikolaos Vasiloglou, RelationalAI. Nikolaos Vasiloglou explains how he distilled NeurIPS into a six-hour presentation and a smaller NotebookLM podcast. He began with keynotes, oral presentations, and workshops, then... - [Fast, Trustworthy, Reliable Voice Agents: MLOps That Blend LLM Annotation with Human QA](https://mlopstalks.com/talks/fast-trustworthy-reliable-voice-agents-mlops-that-blend-llm-annotation-with): Erik Goron, HappyRobot. Erik Goron describes how HappyRobot moved from manually tuning voice-agent behavior to a production MLOps approach. The system tracks north-star metrics such as user frustration,... - [From Spikes to Stories: AI-Augmented Troubleshooting in the Network Wild](https://mlopstalks.com/talks/from-spikes-to-stories-ai-augmented-troubleshooting-in-the-network-wild): Shraddha Yeole, Cisco ThousandEyes. Shraddha Yeole describes how Cisco ThousandEyes is moving from dashboards that present telemetry to an AI assistant that interprets it. She uses a Spotify availability... - [How Agent Memory Will Change Your Organization](https://mlopstalks.com/talks/how-agent-memory-will-change-your-organization): Devin Stein, Dosu. Devin Stein describes Dosu's new agent architecture, which combines retrieval with deeper agent research. Dosu originally used asynchronous agents for GitHub issues, where a two-to-ten-minute... - [The Hidden Infrastructure Behind Every AI Agent](https://mlopstalks.com/talks/the-hidden-infrastructure-behind-every-ai-agent): Erica Hughberg, Tetrate. Erica Hughberg explains why AI agents need infrastructure beyond a conventional API gateway. A simple instruction can trigger calls to OpenAI, Bedrock, Anthropic, Gemini, internal... - [Too much lock-in for too little gain: agent frameworks are a dead-end](https://mlopstalks.com/talks/too-much-lock-in-for-too-little-gain-agent-frameworks-are-a-dead-end): Valliappa Lakshmanan. Valliappa Lakshmanan argues that agent frameworks often add lock-in without giving teams enough value in return. He proposes building agents as small, independently implemented components... - [AI traces are worth a thousand logs](https://mlopstalks.com/talks/ai-traces-are-worth-a-thousand-logs): . David presents a simple model of how agent frameworks work. An agent has instructions, tools, and a language model. The model runs in a loop,... - [Voice model performance optimization](https://mlopstalks.com/talks/voice-model-performance-optimization): Madison Kanna, Baseten. Madison Kanna and her Baseten colleague explain how to run speech-to-text and text-to-speech models with lower latency and higher concurrency. They separate latency measures such... - [APICA: The Digital Colleague at the Port of Antwerp-Bruges](https://mlopstalks.com/talks/apica-the-digital-colleague-at-the-port-of-antwerp-bruges): Pierre Gerardi, Port of Antwerp-Bruges. Pierre Gerardi presents APICA, a multi-agent application intended to become the digital colleague for Port of Antwerp-Bruges employees. Users interact with it through a Teams... - [Deploying Executable Agent Workflows](https://mlopstalks.com/talks/deploying-executable-agent-workflows): Gal Peretz, Carbyne. Gal Peretz compares traditional JSON tool calling with CodeAct, where an LLM writes Python and runs it in a sandbox. He argues that JSON schemas... - [Integration of AI into Traditional Systems](https://mlopstalks.com/talks/integration-of-ai-into-traditional-systems): Hakan Tek. Hakan Tek explains how companies can add AI to older systems that remain important to daily operations. He describes the main obstacles as outdated technology,... - [Iterating on Your AI Evals](https://mlopstalks.com/talks/iterating-on-your-ai-evals): Mariana Prazeres. Mariana Prazeres explains why the last step from an AI demo to a reliable product is difficult. Small prompt changes can make a demo look... - [How Agents Changed Vibe Coding Forever](https://mlopstalks.com/talks/how-agents-changed-vibe-coding-forever): Beyang Liu, Sourcegraph. Beyang Liu describes a shift from autocomplete and chat-based coding assistants to agents that can reason, use tools, find context, and validate their own work.... - [Evaluation-Driven Development with MLflow 3.0](https://mlopstalks.com/talks/evaluation-driven-development-with-mlflow-3-0): Yuki Watanabe, Databricks. Yuki Watanabe presents Evaluation-Driven Development as a way to build agentic applications with more confidence. He compares it with test-driven development, with evaluations providing the... - [AI Changed Stack Overflow for the Better](https://mlopstalks.com/talks/ai-changed-stack-overflow-for-the-better): Prashanth Chandrashekar, Stack Overflow. Prashanth Chandrashekar explains how Stack Overflow is adapting as developers use AI tools for more coding questions. Basic questions are increasingly handled by chatbots, while... - [How AI Will Transform The Energy Sector](https://mlopstalks.com/talks/how-ai-will-transform-the-energy-sector): Adam Sroka, Hypercube. Adam Sroka describes Jellyfish, Hypercube's agentic AI platform for managing renewable energy projects. He starts with the long, expensive process of developing assets such as... - [How Reinforcement Learning Can Improve Your Agent](https://mlopstalks.com/talks/how-reinforcement-learning-can-improve-your-agent): Patrick Barker. Patrick Barker argues that agent reliability gets worse as systems move from simple interactions to multi-step, multi-tool and autonomous work. Prompting cannot currently fix many... - [I Built A Trustworthy Voice Assistant](https://mlopstalks.com/talks/i-built-a-trustworthy-voice-assistant): . Allegra explains why voice agents need different design choices from text-based agents. She describes modular systems that convert speech to text, use an LLM, and... - [Why Language Models Need a Lesson in Education](https://mlopstalks.com/talks/why-language-models-need-a-lesson-in-education): Stephanie Kirmer, DataGrail. Stephanie Kirmer applies her experience teaching college classes to LLM evaluation. She argues that teams should not put an LLM into production based on confidence... - [Knowledge is Eventually Consistent](https://mlopstalks.com/talks/knowledge-is-eventually-consistent): Devin Stein, Dosu. Devin Stein describes how Dosu evolved from answering questions and triaging issues into a fact-based reasoning agent for product and engineering knowledge. The agent researches... - [Traditional vs LLM Recommender Systems: Are They Worth It?](https://mlopstalks.com/talks/traditional-vs-llm-recommender-systems-are-they-worth-it): Arpita Vats, LinkedIn. Arpita Vats compares traditional recommender systems with LLM-based approaches through examples from content feeds and sequential recommendations. Traditional systems depend on explicit features, user clusters,... - [Advanced Context Engineering](https://mlopstalks.com/talks/advanced-context-engineering): . Dex argues that production agents are mostly software with LLM calls placed where they add value. Frameworks help teams get an early system running, but... - [How Synthetic Data Will Transform Publishing Forever](https://mlopstalks.com/talks/how-synthetic-data-will-transform-publishing-forever): Robert Caulk, Emergent Methods. Robert Caulk argues that publishers need a different business model as AI agents retrieve information directly instead of sending users to websites. Direct licensing with... - [The Science of Improving AI Agents](https://mlopstalks.com/talks/the-science-of-improving-ai-agents): . Shahul presents Eval-Driven Development as a practical way to improve AI agents through experiments instead of subjective "vibe checks." He recommends starting with end-to-end metrics... - [When Agents Hire Their Own Team: Inside Hypermode's Concierge](https://mlopstalks.com/talks/when-agents-hire-their-own-team-inside-hypermodes-concierge): Ryan Fox-Tyler, Hypermode. Ryan Fox-Tyler explains how Hypermode built Concierge, an agent that creates other agents. The system starts with a short natural-language description, gathers missing context, connects... - [Prepare Your Data for AI Now, or You're Screwed Later](https://mlopstalks.com/talks/prepare-your-data-for-ai-now-or-youre-screwed-later): Simba Khadder, Featureform. Simba Khadder argues that agent quality is limited by data access more often than by model intelligence. A retrieval system can explain common delivery delays,... - [The Truth About LLM Training](https://mlopstalks.com/talks/the-truth-about-llm-training): Paul van der Boor & Zulkuf Genc, Prosus Group. Paul van der Boor and Zulkuf Genc explain how Prosus evaluates, trains, and runs models for products used across its group companies. Their evaluation system... - [The Hidden Bottlenecks Slowing Down AI Agents](https://mlopstalks.com/talks/the-hidden-bottlenecks-slowing-down-ai-agents): Paul van der Boor & Bruce Martens, Prosus Group. Paul van der Boor and Bruce Martens explain why buying tools has not removed the hardest work in agent development. Evaluation depends on curated datasets,... - [AI Coding Agents Change Software Development Forever](https://mlopstalks.com/talks/ai-coding-agents-change-software-development-forever): Michele Catasta, Replit & Aparna Dhinakaran, Arize AI & Erik Schluntz, Anthropic. This panel discusses where coding agents help and where they still create risk. Erik Schluntz says the terminal is a common interface for agents, while... - [9 Commandments Building AI Agents](https://mlopstalks.com/talks/9-commandments-building-ai-agents): Paul van der Boor & Dmitri Jarnikov, Prosus Group. The discussion explains why agents often create more work than they remove. Paul van der Boor describes interfaces that guide users with buttons and structured... - [Why Enterprise AI is Taking So Long to Implement](https://mlopstalks.com/talks/why-enterprise-ai-is-taking-so-long-to-implement): Paul van der Boor & Sean Kenny, Prosus Group. Paul van der Boor and Sean Kenny explain why enterprise AI adoption takes more than making a model available. Prosus started with language models in... - [Real-time Feature Generation at Lyft](https://mlopstalks.com/talks/real-time-feature-generation-at-lyft): Rakesh Kumar, Lyft. Rakesh Kumar explains how Lyft generates features from marketplace events for use cases such as demand and supply forecasting and surge pricing. The platform processes... - [MLflow 3.0: The Future of AI Agents](https://mlopstalks.com/talks/mlflow-3-0-the-future-of-ai-agents): Eric Peter, Databricks. Eric Peter compares the traditional MLOps lifecycle with the development lifecycle for GenAI applications and agents. Training is often replaced by prompting, tuning, tool use,... - [AI Agent Development Tradeoffs You NEED to Know](https://mlopstalks.com/talks/ai-agent-development-tradeoffs-you-need-to-know): Sherwood Callaway, 11X. Sherwood Callaway explains how 11X builds Alice, an AI sales development representative, and Julian, a voice agent for inbound sales. He compares text and voice... - [From the Legal Trenches to Tech](https://mlopstalks.com/talks/from-the-legal-trenches-to-tech): Nick Coleman, LexMed. Nick Coleman explains how his work as a Social Security disability attorney led him to build LexMed. Attorneys must assemble evidence from large medical records,... - [The Rise of Sovereign AI and Global AI Innovation in a World of US Protectionism](https://mlopstalks.com/talks/the-rise-of-sovereign-ai-and-global-ai-innovation-in-a-world-of-us-protectionism): Frank Meehan, Frontier One AI. Frank Meehan argues that sovereign AI has become a national priority because governments want sensitive defense, health, finance, and agriculture data to stay inside their... - [A New Way of Building with AI](https://mlopstalks.com/talks/a-new-way-of-building-with-ai): Jiquan Ngiam, Lutra AI. Jiquan Ngiam describes Lutra as an AI agent that completes work across email, spreadsheets, CRM systems, and other applications. He focuses on ordinary jobs such... - [Building AI that Doesn't Break](https://mlopstalks.com/talks/building-ai-that-doesnt-break): Elliot Gunton, Pipekit & Qian Li, DBOS, Inc. & Alan Nichol, Rasa. This mini summit brings together three approaches to making AI systems easier to run when failures, delays, and changing inputs are unavoidable. Elliot Gunton presents... - [Inside Uber's AI Revolution: Everything About How They Use AI/ML](https://mlopstalks.com/talks/inside-ubers-ai-revolution-everything-about-how-they-use-ai-ml): Kai Wang, Uber. Kai Wang explains how Uber built Michelangelo after teams began creating separate, hard-to-manage machine learning workflows around 2015. The platform now provides templates and pipelines... - [The Missing Data Stack for Physical AI](https://mlopstalks.com/talks/the-missing-data-stack-for-physical-ai): Nikolaus West, Rerun. Nikolaus West defines physical AI as software that applies intelligence to the physical world. The category includes robotics, spatial computing, and systems that analyze real-world... - [ML Engineers Who Ignore LLMs Are Voluntarily Retiring Early](https://mlopstalks.com/talks/ml-engineers-who-ignore-llms-are-voluntarily-retiring-early): Kostas Pardalis & Yoni Michael, Typedef. Kostas Pardalis and Yoni Michael argue that LLMs are changing the work of data and ML engineers. Existing platforms were designed around structured, tabular data... - [Testing AI Intelligence: The Benchmarking Battle](https://mlopstalks.com/talks/testing-ai-intelligence-the-benchmarking-battle): Greg Kamradt, Arc Prize. Greg Kamradt explains why Arc Prize uses benchmarks built around tasks that are easy for capable humans but difficult for AI. Arc AGI 1 and... - [How AI is Transforming Business Data Forever](https://mlopstalks.com/talks/how-ai-is-transforming-business-data-forever): Deepti Srivastava, Snow Leopard AI. Deepti Srivastava argues that enterprise AI will remain limited until it can use operational business data directly. Most current applications sit beside production systems and... - [The Creator of FastAPI's Next Chapter](https://mlopstalks.com/talks/the-creator-of-fastapis-next-chapter): Sebastián Ramírez, FastAPI Labs. Sebastián Ramírez explains how his machine learning background led him to FastAPI, after repeated difficulty building APIs around computer vision and other applications. Pydantic became... - [Everything Hard About Building AI Agents Today](https://mlopstalks.com/talks/everything-hard-about-building-ai-agents-today): Shreya Shankar & Willem Pienaar, Cleric. Shreya Shankar and Willem Pienaar discuss why production AI agents are difficult to evaluate and improve. Willem describes Cleric, an agent that investigates production alerts... - [Packaging MLOps Tech Neatly for Engineers and Non-engineers](https://mlopstalks.com/talks/packaging-mlops-tech-neatly-for-engineers-and-non-engineers): Jukka Remes, Haaga-Helia University of Applied Sciences, 8wave AI. Jukka Remes explains how a platform developed at Silo AI became an open-source setup for researchers, engineers, and organizations that need MLOps without relying on... - [Office Hours on DuckDB, AWS Glue, and Iceberg](https://mlopstalks.com/talks/office-hours-on-duckdb-aws-glue-and-iceberg): . Eric, Hossam, and Demetrios explain how analytical databases differ from transactional databases, then build toward a serverless lakehouse using S3, Apache Parquet, Iceberg, and the... - [Hard Learned Lessons from Over a Decade in AI](https://mlopstalks.com/talks/hard-learned-lessons-from-over-a-decade-in-ai): Mike Del Balso, Tecton. Mike Del Balso explains what he learned building production ML systems at Google, Uber, and Tecton. He describes how Uber moved from scattered ML experiments... - [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlopstalks.com/talks/mem0-building-production-ready-ai-agents-with-scalable-long-term-memory): Nehil Jain, Stealth AI Startup & David DeStefano, Adonis. The paper discussed is "Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory." Prateek Chhikara, a co-author and founding AI engineer at Mem0, explains how... - [How Product Metrics Become LLM Evaluations](https://mlopstalks.com/talks/how-product-metrics-become-llm-evaluations): Raza Habib, Humanloop. Raza Habib argues that product metrics and LLM evaluations should measure nearly the same thing: whether a user achieved the outcome they wanted. Since generative... - [RAG from Scratch with Best Practices](https://mlopstalks.com/talks/rag-from-scratch-with-best-practices): Skylar Payne. Skylar Payne builds a documentation chatbot live, starting with a hard-coded terminal chat app. He adds Lilyad tracing before changing the system, then collects four... - [Getting AI Apps Past the Demo](https://mlopstalks.com/talks/getting-ai-apps-past-the-demo): Vaibhav Gupta, BoundaryML. Vaibhav Gupta explains why many AI applications remain demo-like after two years of rapid development. He sees prompt code written as large, dynamic strings, often... - [Tricks to Fine Tuning](https://mlopstalks.com/talks/tricks-to-fine-tuning): Prithviraj Ammanabrolu, Databricks. Prithviraj Ammanabrolu explains Tao, or test-time adaptive optimization, as a way to fine-tune models for private, domain-specific tasks using prompts instead of labeled answers. A... - [Building Out GPU Clouds](https://mlopstalks.com/talks/building-out-gpu-clouds): Mohan Atreya, Rafay Systems. Mohan Atreya explains why GPU infrastructure is harder to provide than ordinary cloud compute. Customers often need a specific GPU, but availability, pricing, long commitments,... - [MCP is not going to change everything (yet)](https://mlopstalks.com/talks/mcp-is-not-going-to-change-everything-yet): Sam Partee, Arcade AI & Rahul Parundekar, AI Hero. The conversation defines an agent as a language model that can pass text into deterministic processes and run them as tools. Tools let models retrieve... - [AI in M&A: Building, Buying, and the Future of Dealmaking](https://mlopstalks.com/talks/ai-in-m-a-building-buying-and-the-future-of-dealmaking): Kison Patel, DealRoom. Kison Patel describes how his M&A background led to DealRoom, after an earlier software business failed when Google treated its linking approach as link farming.... - [MLOps with Databricks](https://mlopstalks.com/talks/mlops-with-databricks): Maria Vechtomova, Ahold Delhaize | Marvelous MLOps. Maria Vechtomova explains why Databricks is often a practical MLOps choice for large companies. A platform reduces the work of combining tools, and vendor approval... - [Building an AI agent with LangGraph, step by step tutorial](https://mlopstalks.com/talks/building-an-ai-agent-with-langgraph-step-by-step-tutorial): . Annie explains how to choose a problem for an AI agent and walks through building a budget coach with LangGraph. She starts with LangGraph Academy's... - [How AI is Revolutionizing Marketing Forever](https://mlopstalks.com/talks/how-ai-is-revolutionizing-marketing-forever): Fausto Albers, AI Builders Club. Fausto Albers and Demetrios Brinkmann discuss how generative AI changes marketing, software building, and human decision-making. Fausto describes a future where pipelines find high-performing ads,... - [AI Agents for Financial Institutions](https://mlopstalks.com/talks/ai-agents-for-financial-institutions): Vamsi Saladi, Contour. Vamsi Saladi explains how Contour builds AI customer support for banks, credit unions, and fintechs. Financial agents operate under tighter constraints because they handle money,... - [Evaluation of Agentic System](https://mlopstalks.com/talks/evaluation-of-agentic-system): Aditya Gautam, Meta. Aditya Gautam explains why evaluating an agentic system requires more than checking a model against a standard benchmark. Agents can plan, call tools, revisit decisions,... - [Making AI Reliable is the Greatest Challenge of the 2020s](https://mlopstalks.com/talks/making-ai-reliable-is-the-greatest-challenge-of-the-2020s): Alon Bochman, RagMetrics. Alon Bochman argues that AI teams have to discover what works through experiments on their own tasks. Vendors, research labs, influencers, and paper authors cannot... - [Iceberg, MCP, and MLOps: Bridging the Gaps for Enterprise](https://mlopstalks.com/talks/iceberg-mcp-and-mlops-bridging-the-gaps-for-enterprise): Caleb Baechtold, Snowflake & Hamza Tahir, ZenML & Simba Khadder, Featureform. This Mini Summit connects three parts of enterprise MLOps. Caleb Baechtold describes Snowflake's approach to bringing feature work, model development, deployment, monitoring, access control, lineage,... - [Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data](https://mlopstalks.com/talks/behavior-modeling-secondary-ai-effects-bias-reduction-synthetic-data): Devansh Devansh, Stealth AI Startup. Devansh Devansh discusses AI as a way to inspect and restructure data, rather than only as a model trained on data. He sees synthetic data... - [A-MEM: Agentic Memory for LLM Agents](https://mlopstalks.com/talks/a-mem-agentic-memory-for-llm-agents): Adam Becker, MLOps Community & Nehil Jain, Stealth AI Startup & Matt Squire, Fuzzy Labs. The paper discussed was A-MEM: Agentic Memory for LLM Agents. Matt Squire introduced its motivation through a DevOps agent that remembers infrastructure failures, approved fixes,... - [GraphBI: Expanding Analytics to All Data Through the Combination of GenAI, Graph, & Visual Analytics](https://mlopstalks.com/talks/graphbi-expanding-analytics-to-all-data-through-the-combination-of-genai-graph): Paco Nathan, Senzing. Paco Nathan and Weidong Yang discuss how graphs can extend analytics beyond structured tables. They start with sensitive financial investigations, where tokenizing personally identifiable information... - [AI Data Engineers: Data Engineering After AI](https://mlopstalks.com/talks/ai-data-engineers-data-engineering-after-ai): Vikram Chennai, Ardent AI. Vikram Chennai describes Ardent AI's AI data engineer as a coding agent connected to an organisation's existing data stack. It can inspect repositories, APIs, schemas,... - [I Am Once Again Asking "What is MLOps?"](https://mlopstalks.com/talks/i-am-once-again-asking-what-is-mlops): Oleksandr Stasyk, Synthesia. Oleksandr Stasyk describes MLOps as the work of helping a business iterate on machine learning efficiently. He compares it with DevOps, while adding the demands... - [How Sama is Improving ML Models to Make AVs Safer](https://mlopstalks.com/talks/how-sama-is-improving-ml-models-to-make-avs-safer): Duncan Curtis, Sama. Duncan Curtis describes Sama as a partner for companies that need better data for AI. He focuses on the human intelligence involved in annotation, where... - [Building Robust AI Systems with Battle-tested Frameworks](https://mlopstalks.com/talks/building-robust-ai-systems-with-battle-tested-frameworks): Vaibhav Gupta, Boundary ML & Charles Frye, Modal. Vaibhav Gupta opens by arguing that an LLM application cannot remain at the 80% accuracy level that is acceptable for a demo. Developers need to... - [AI-Powered Product Ideation with Synthetic Consumer Testing](https://mlopstalks.com/talks/ai-powered-product-ideation-with-synthetic-consumer-testing): Luca Fiaschi, PyMC Labs. Luca Fiaschi describes how he combines traditional machine learning, Bayesian modeling, and generative AI to speed up analytics work. Bayesian models help explain forecasts, express... - [Build a Slack Agent with Pydantic AI](https://mlopstalks.com/talks/build-a-slack-agent-with-pydantic-ai): . This tutorial builds a Slack digest agent with Pydantic AI. The agent connects to Slack, fetches messages and replies, summarizes individual threads, and produces a... - [Real-Time Forecasting Faceoff: Time Series vs. DNNs](https://mlopstalks.com/talks/real-time-forecasting-faceoff-time-series-vs-dnns): Josh Xi, Lyft. Josh Xi describes forecasting demand and supply for Lyft's marketplace at geohash level. The system may forecast every five minutes through the next hour across... - [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlopstalks.com/talks/which-economic-tasks-are-performed-with-ai-evidence-from-millions-of-claude): Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sophia Skowronski, Breckinridge Capital Advisors. Sophia Skowronski introduces a framework from Anthropic's paper that maps four million Claude conversations to 20,000 O*NET tasks and about 1,000 occupations. The analysis estimates... - [We're All Finetuning Incorrectly](https://mlopstalks.com/talks/were-all-finetuning-incorrectly): Tanmay Chopra, Emissary. Tanmay Chopra argues that many teams call extended pretraining or prompt changes fine-tuning, while missing the older machine learning practices that make systems improve for... - [From Shiny to Strategic: The Maturation of AI Across Industries](https://mlopstalks.com/talks/from-shiny-to-strategic-the-maturation-of-ai-across-industries): David Cox, RethinkFirst; Institute of Applied Behavioral Science. David Cox discusses AI through the lens of behavioral science rather than LLMs. His work examines how environmental signals, wearable data, clinical observations, and other... - [Streaming Ecosystem Complexities and Cost Management](https://mlopstalks.com/talks/streaming-ecosystem-complexities-and-cost-management): Rohit Agrawal, Tecton. Rohit Agrawal explains why real-time ML data systems become difficult to build and expensive to run. A typical pipeline connects Kafka or Kinesis to Spark... - [Fraud Detection in the AI Era](https://mlopstalks.com/talks/fraud-detection-in-the-ai-era): Rafael Sandroni, GardionAI. Rafael Sandroni discusses the overlap between AI security and fraud detection. Drawing on work with Siri, Nubank, and GardionAI, he argues that AI assistants require... - [Efficient GPU infrastructure at LinkedIn](https://mlopstalks.com/talks/efficient-gpu-infrastructure-at-linkedin): Animesh Singh, LinkedIn. Animesh Singh describes how LinkedIn moved from early LLM experiments to products such as profile summarization, personalized recruiter emails, and the LinkedIn Hiring Assistant. He... - [Beyond the Matrix: AI and the Future of Human Creativity](https://mlopstalks.com/talks/beyond-the-matrix-ai-and-the-future-of-human-creativity): Fausto Albers, AI Builders Club. Fausto Albers and Demetrios Brinkmann discuss how AI could reduce the effort required to think, search, collaborate, and make decisions. Albers describes an AI analyzer... - [Comparing ZenML, Metaflow, and all the other DAG tools](https://mlopstalks.com/talks/comparing-zenml-metaflow-and-all-the-other-dag-tools): . The discussion compares ZenML and Metaflow with general workflow tools such as Prefect and compute platforms such as Modal. Ben argues that many teams can... - [Building Trust Through Technology: Responsible AI in Practice](https://mlopstalks.com/talks/building-trust-through-technology-responsible-ai-in-practice): Allegra Guinan, Lumiera. Allegra Guinan defines responsible AI as an approach to designing, developing, deploying, using, and regulating AI around principles such as fairness, accountability, transparency, explainability, privacy,... - [From Rules to Reasoning Engines](https://mlopstalks.com/talks/from-rules-to-reasoning-engines): George Mathew, Insight Partners. George Mathew describes a shift from software built around encoded rules to AI systems that can reason, coordinate agents, and carry out work. He expects... - [GenAI Traffic: Why API Infrastructure Must Evolve... Again](https://mlopstalks.com/talks/genai-traffic-why-api-infrastructure-must-evolve-again): Erica Hughberg, Tetrate. Erica Hughberg traces the evolution of API infrastructure from the C10K problem through event-driven proxies, monolith-to-microservices migrations, Kubernetes scheduling, and Envoy. Each shift addressed a... - [AI in Production 2025 | Keynote](https://mlopstalks.com/talks/ai-in-production-2025-keynote): . The keynote explains how guardrails fit into AI applications and why they need the same testing discipline as other machine learning systems. Guardrails can inspect... - [Unbearable Lightness of Data: The Weight of Information](https://mlopstalks.com/talks/unbearable-lightness-of-data-the-weight-of-information): Rohit Krishnan, Bodo.AI. Rohit Krishnan and Demetrios Brinkmann discuss how people should interact with reasoning models, especially systems that produce long reports after searching and thinking for several... - [Kubernetes, AI Gateways, and the Future of MLOps](https://mlopstalks.com/talks/kubernetes-ai-gateways-and-the-future-of-mlops): Alexa Griffith, Bloomberg. Alexa Griffith describes her path from computational chemistry into software engineering, beginning with operational problems in Airflow and Kubernetes. She explains how those experiences led... - [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlopstalks.com/talks/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-reinforcement): Adam Becker, MLOps Community & Nehil Jain, Stealth AI Startup & Matt Squire, Fuzzy Labs & Sophia Skowronski, Breckinridge Capital Advisors. The paper DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning describes how DeepSeek used reinforcement learning to produce a model that reasons through difficult... - [I Let An AI Play Pokémon! - Claude plays Pokémon Creator](https://mlopstalks.com/talks/i-let-an-ai-play-pokemon-claude-plays-pokemon-creator): David Hershey, Anthropic. David Hershey explains how he built Claude Plays Pokémon to explore agents in a setting that requires thousands of decisions over many hours. Claude presses... - [Future of Software, Agents in the Enterprise, and Inception Stage Company Building](https://mlopstalks.com/talks/future-of-software-agents-in-the-enterprise-and-inception-stage-company-building): Eliot Durbin, Boldstart Ventures. Eliot Durbin describes Boldstart Ventures' inception-stage approach and the founder traits he looks for after years of making first-check investments. He backs people with a... - [The Agent Exchange: Practitioner Insights](https://mlopstalks.com/talks/the-agent-exchange-practitioner-insights): Dmitri Jarnikov & Chiara Caratelli, Prosus Group & Steven Vester, OLX. This episode examines two questions about AI agents in e-commerce: whether generic or specialized agents will win, and what happens to companies that make shopping... - [AI SQL Data Analyst](https://mlopstalks.com/talks/ai-sql-data-analyst): Paul van der Boor & Donne Stevenson, Prosus Group. Paul van der Boor and Donne Stevenson describe how Prosus Group productionized a Toqan Data Analyst agent that answers questions about company data in shared... - [The Future of AI: Building Multi-Agent Systems](https://mlopstalks.com/talks/the-future-of-ai-building-multi-agent-systems): . The speaker argues that strong LLM benchmark results do not automatically produce useful enterprise products. Business-specific constraints, messy data, large tool sets, and higher expectations... - [Web Agents: The Cutting Edge of AI is Here?](https://mlopstalks.com/talks/web-agents-the-cutting-edge-of-ai-is-here): Paul van der Boor & Chiara Caratelli, Prosus Group. Paul van der Boor and Chiara Caratelli explain why Prosus Group is building agents that use websites through browsers. APIs do not expose every action... - [AI Agents: The Evolution of Our Digital Friends](https://mlopstalks.com/talks/ai-agents-the-evolution-of-our-digital-friends): . The talk explains AI agents through a Mars rover built from a Raspberry Pi, sensors, a camera, and memory. An LLM provides the reasoning, while... - [The Challenge with AI Voice Agents](https://mlopstalks.com/talks/the-challenge-with-ai-voice-agents): Paul van der Boor & Floris Fok, Prosus Group. Demetrios Brinkmann, Paul van der Boor, and Floris Fok discuss why voice agents behave differently from text agents. Paul describes the move from separate speech... - [The Agent Landscape - Lessons Learned Putting Agents Into Production](https://mlopstalks.com/talks/the-agent-landscape-lessons-learned-putting-agents-into-production): Paul van der Boor & Floris Fok, Prosus Group. Demetrios Brinkmann, Paul van der Boor, and Floris Fok discuss how Prosus Group experiments with agents across its portfolio companies. Paul defines an agent as... - [Look At Your ****ing Data 👀](https://mlopstalks.com/talks/look-at-your-ing-data): Kenny Daniel, Hyperparam. Kenny Daniel argues that data is still the least examined part of modern AI development. Companies discuss model architectures and hardware, while training data, filtering,... - [Building AI That Remembers You](https://mlopstalks.com/talks/building-ai-that-remembers-you): Sarah Wooders, Letta. Sarah Wooders presents Letta as an open source framework and platform for stateful agents. Its main responsibility is context management: collecting agent state, memories, tools,... - [Evolving Workflow Orchestration](https://mlopstalks.com/talks/evolving-workflow-orchestration): Alex Milowski, Entrepreneur and Computer Scientist. Alex Milowski explains how workflow orchestration grew from business process systems and rule engines into the tools used for data engineering and MLOps. He describes... - [AI Agents: The Future of ML Engineering?](https://mlopstalks.com/talks/ai-agents-the-future-of-ml-engineering): Matt Squire, Fuzzy Labs & Adam Becker, MLOps Community. The paper MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering introduces a benchmark built from 75 Kaggle competitions. The paper's authors give agents competition... - [Autonomous AI SRE: The Future of Site Reliability Engineering](https://mlopstalks.com/talks/autonomous-ai-sre-the-future-of-site-reliability-engineering): Willem Pienaar, Cleric. Willem Pienaar explains why an autonomous AI SRE is harder to build than a general coding agent. Production systems are sprawling, dynamic, and full of... - [The Battle for AI: Robustness vs Privacy](https://mlopstalks.com/talks/the-battle-for-ai-robustness-vs-privacy): Vinu Sankar Sadasivan, Google DeepMind. Vinu Sankar Sadasivan explains why AI-generated text detection remains difficult even when models use watermarks. He describes four detector types, including watermarks, trained classifiers, zero-shot... - [Scaling your data and AI from 0-100 with open source](https://mlopstalks.com/talks/scaling-your-data-and-ai-from-0-100-with-open-source): Maarten Breddels, Pycafe & Pranav Aurora, Mooncake & Simba Khadder, Featureform. This session presents three open-source-oriented tools for moving from small experiments to production data and AI systems. Maarten Breddels introduces Pycafe, a browser-based environment for... - [AI & Aliens: New Eyes on Ancient Questions](https://mlopstalks.com/talks/ai-aliens-new-eyes-on-ancient-questions): Richard Cloete, Harvard University and SEAQR Robotics. Richard Cloete describes how he applies machine learning to questions about unusual objects in the sky, interstellar objects, and the ocean. For the Galileo Project,... - [Real LLM Success Stories: How They Actually Work](https://mlopstalks.com/talks/real-llm-success-stories-how-they-actually-work): Alex Strick van Linschoten, ZenML. Alex Strick van Linschoten explains why he built ZenML's database of real-world LLM use cases. Inspired by Evidently, he collected scattered case studies, podcast episodes,... - [AI Careers Insights from Ex Meta Staff Eng](https://mlopstalks.com/talks/ai-careers-insights-from-ex-meta-staff-eng): Ilya Reznik, Instructed Machines, LLC. Ilya Reznik discusses two connected subjects: practical choices around large language models and the career path for machine learning engineers. He argues that teams should... - [Building a Decentralized Knowledge Graph for AI](https://mlopstalks.com/talks/building-a-decentralized-knowledge-graph-for-ai): Tomaž Levak, OriginTrail. Tomaž Levak explains how OriginTrail's Decentralized Knowledge Graph connects privately managed knowledge graphs into a shared protocol. Organizations can keep their data inside their own... - [Efficient Deployment of Models at the Edge](https://mlopstalks.com/talks/efficient-deployment-of-models-at-the-edge): Krishna Sridhar, Qualcomm. Krishna Sridhar explains why deploying AI at the edge is difficult and why it is useful. Phones already run many models for photography, speech, and... - [Real World AI Agent Stories](https://mlopstalks.com/talks/real-world-ai-agent-stories): Zach Wallace, Nearpod Inc.. Zach Wallace describes how Nearpod moved from a fragmented data architecture toward a system built with dbt, Redshift, Snowflake, S3, and domain-oriented data products. He... - [Machine Learning, AI Agents, and Autonomy](https://mlopstalks.com/talks/machine-learning-ai-agents-and-autonomy): Egor Kraev, Wise Plc. Egor Kraev discusses how Wise uses machine learning across financial crime, treasury, customer support, and marketing. He sees the most reliable LLM applications as small... - [Re-Platforming Your Tech Stack](https://mlopstalks.com/talks/re-platforming-your-tech-stack): Michelle Marie Conway & Andrew Baker, Lloyds Banking Group. Michelle Marie Conway and Andrew Baker discuss Lloyds Banking Group's move from on-premises infrastructure to Google Cloud. Their team maintained around 10 production models and... - [How AgentOps Enables Observability](https://mlopstalks.com/talks/how-agentops-enables-observability): Nehil Jain, Stealth AI Startup & Adam Becker, MLOps Community & Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Binoy Perera, MLOps Community. The session discusses the paper A Taxonomy of AgentOps for Enabling Observability of Foundation Model-based Agents. Nehil Jain introduces agents through four capabilities: perception, planning... - [Autonomous Multi Agent AI Systems](https://mlopstalks.com/talks/autonomous-multi-agent-ai-systems): . Natan describes agents as autonomous units that use language models, tools, and system instructions to perform tasks. Teams of agents can divide work such as... - [Why Pydantic AI is the Future of AI Agents](https://mlopstalks.com/talks/why-pydantic-ai-is-the-future-of-ai-agents): Samuel Colvin, Pydantic. Samuel Colvin explains why the Pydantic team built Pydantic AI after finding existing agent frameworks unsuitable for the production applications they wanted to build. Pydantic... - [Holistic Evaluation of Generative AI Systems](https://mlopstalks.com/talks/holistic-evaluation-of-generative-ai-systems): Jineet Doshi, Intuit. Jineet Doshi explains why generative AI evaluation remains difficult. Traditional machine learning models had narrow tasks, bounded outputs, and established metrics. LLMs can write, summarize,... - [State of AI Report 2024](https://mlopstalks.com/talks/state-of-ai-report-2024): Nathan Benaich, Air Street Capital. Nathan Benaich presents an editor's cut of the 2024 State of AI Report, covering research, industry, politics, safety, and predictions. He describes OpenAI's early frontier... - [Building an ML Platform from scratch](https://mlopstalks.com/talks/building-an-ml-platform-from-scratch): . Ben Eric and Demetrios Brinkmann continue a live build of an MLOps platform around SQLMesh and DuckDB. They fix SQL quoting and timestamp issues, inspect... - [Unleashing Unconstrained News Knowledge Graphs to Combat Misinformation](https://mlopstalks.com/talks/unleashing-unconstrained-news-knowledge-graphs-to-combat-misinformation): Robert Caulk, Emergent Methods. Robert Caulk explains how Emergent Methods builds AskNews, a real-time news retrieval service based on a large, unconstrained knowledge graph. Instead of forcing every article... - [Why Agents Are Stupid & What We Can Do About It](https://mlopstalks.com/talks/why-agents-are-stupid-what-we-can-do-about-it): Dan Jeffries, Kentauros AI. Dan Jeffries argues that current frontier models are far from general agents. A real agent has to complete open-ended tasks in the physical or digital... - [Goal Oriented Retrieval Agents](https://mlopstalks.com/talks/goal-oriented-retrieval-agents): Zoe Weil, Faber Labs. Zoe Weil presents GORA, or Goal-Oriented Retrieval Agents, as a retrieval and ranking system built around measurable client outcomes. Faber Labs uses it in e-commerce... - [Is More Really Better: Delve Into Document Strategy](https://mlopstalks.com/talks/is-more-really-better-delve-into-document-strategy): . This session examines how the number of retrieved documents, in-context examples, retrieval iterations, and context length affect RAG performance. The speaker explains a model that... - [LLM Distillation and Compression](https://mlopstalks.com/talks/llm-distillation-and-compression): Guanhua "Alex" Wang, Microsoft. Guanhua "Alex" Wang discusses how Microsoft trained and compressed small language models, drawing on his work with Phi-3 and DeepSpeed. He says Phi-3 depended on... - [Simulation Techniques for AI Agents from Self-Driving](https://mlopstalks.com/talks/simulation-techniques-for-ai-agents-from-self-driving): Brooke Hopkins, Coval. Brooke Hopkins compares autonomous AI agents with self-driving cars. Both perceive an environment, make decisions, and act across a sequence of changing situations. She argues... - [How to Create a Multi-Agent AI System in JavaScript](https://mlopstalks.com/talks/how-to-create-a-multi-agent-ai-system-in-javascript): . Dariel presents KaibanJS as a JavaScript-native framework for building multi-agent systems. He argues that JavaScript developers already work across browsers, servers, and other devices, and... - [Exploring SQLmesh](https://mlopstalks.com/talks/exploring-sqlmesh): . Ben and Demetrios Brinkmann use DuckDB, Runescape marketplace data, and Prefect as a practical setting for exploring SQLmesh. They first discuss DuckDB's limits as a... - [AI's Next Frontier](https://mlopstalks.com/talks/ais-next-frontier): Aditya Naganath, Kleiner Perkins. Aditya Naganath discusses how he evaluates AI companies and why many earlier MLOps startups failed to become large businesses. He looks for a novel approach,... - [Building Reliable Agents](https://mlopstalks.com/talks/building-reliable-agents): Eno Reyes, Factory.ai. Eno Reyes explains how Factory.ai approaches reliability for systems that automate software engineering work. He defines agentic systems through planning, decision-making, and environmental grounding. Plans... - [Building Replit Agent - Hard Lessons Learned](https://mlopstalks.com/talks/building-replit-agent-hard-lessons-learned): . James describes the lessons Replit learned while building and scaling Replit Agent, a coding agent inside its online development environment. The first lesson is to... - [Maximize Your Productivity with LLMs: Task Utility Explained](https://mlopstalks.com/talks/maximize-your-productivity-with-llms-task-utility-explained): Julia Kiseleva, MultiOn. Julia Kiseleva presents AgentEval, a framework for assessing the utility of LLM-powered applications. She starts with a problem in user-facing machine learning: many tasks, such... - [Hugging Face Cofounder on AI Agents, LLMs and Open Source](https://mlopstalks.com/talks/hugging-face-cofounder-on-ai-agents-llms-and-open-source): Thomas Wolf, Hugging Face & Euro Beinat, Prosus Group. Thomas Wolf describes Hugging Face as a community-driven platform that grew from early work on transfer learning and NLP into a home for models, datasets,... - [How to Make AI Agents that ACTUALLY WORK](https://mlopstalks.com/talks/how-to-make-ai-agents-that-actually-work): Patrick Marlo, Google. Patrick Marlo shares lessons from building generative AI agents with developers, customers, and partners. He argues that an agent in production is a software system,... - [Hundreds of Users Love Our Data Analyst AI Agent](https://mlopstalks.com/talks/hundreds-of-users-love-our-data-analyst-ai-agent): Ioannis Zempekakis & Donné Stevenson. Ioannis Zempekakis and Donné Stevenson describe how their English-language data analyst agent moved from an unreliable prototype to a product used by hundreds of people.... - [Knowledge as a Service](https://mlopstalks.com/talks/knowledge-as-a-service): Prashanth Chandrasekar, Stack Overflow. Prashanth Chandrasekar describes Stack Overflow as a large, structured source of human knowledge for AI systems. He says the platform has accumulated close to 60... - [Why Planning is the New Search](https://mlopstalks.com/talks/why-planning-is-the-new-search): . Fabian argues that much knowledge work is repeated searching across inboxes, files, business systems, and conversations, followed by decisions and actions. This work is difficult... - [AI Agents Are Revolutionizing E-Commerce](https://mlopstalks.com/talks/ai-agents-are-revolutionizing-e-commerce): Nishikant Dhanuka & Beatriz Ferreira, OLX. Nishikant Dhanuka and Beatriz Ferreira describe OLX Magic, a shopping assistant for OLX's secondhand marketplace. It accepts natural-language requests, images, and other forms of input,... - [The Open Source AI Coding Revolution](https://mlopstalks.com/talks/the-open-source-ai-coding-revolution): Graham Neubig, All Hands AI. Graham Neubig describes coding agents that work through complete software issues instead of only suggesting lines of code. He demonstrates OpenHands using agents to add... - [How AI Agents Will Change Customer Support](https://mlopstalks.com/talks/how-ai-agents-will-change-customer-support): . Neil describes what Gradient Labs has learned while running an AI agent for complex customer support. He separates the production problem into external integrations, model... - [The Future of Healthcare: AI is Here](https://mlopstalks.com/talks/the-future-of-healthcare-ai-is-here): . Shaun describes the administrative phone work that supports healthcare, including insurance verification, prior authorizations, credentialing, referrals, and claims. Providers often rely on call centers because... - [We're Using AI Agents at Work (and it's amazing)](https://mlopstalks.com/talks/were-using-ai-agents-at-work-and-its-amazing): Euro Beinat, Prosus Group. Euro Beinat and Paul van der Boor describe two AI-agent systems built at Prosus. Toan is an internal assistant available through Slack, the web, and... - [PyTorch for Control Systems and Decision Making](https://mlopstalks.com/talks/pytorch-for-control-systems-and-decision-making): Vincent Moens, Meta. Vincent Moens discusses practical ways to make PyTorch code faster and easier to maintain, with examples from reinforcement learning and TorchRL. He explains why pinned... - [AI Agents: The Future of Productivity, or Just a Fad?](https://mlopstalks.com/talks/ai-agents-the-future-of-productivity-or-just-a-fad): Sam Partee, Arcade AI. Sam Partee explains what tool calling does and why he thinks it is the part that makes an AI system agentic. A language model predicts... - [Few Shot Code Generation to Autonomous Software Engineering Agents](https://mlopstalks.com/talks/few-shot-code-generation-to-autonomous-software-engineering-agents): John Yang, Stanford University. John Yang presents three connected pieces of work on AI systems for software engineering: SWE-bench, SWE-agent, and later work on broader evaluation. SWE-bench turns real... - [How AI Agents Are Transforming Data Analytics](https://mlopstalks.com/talks/how-ai-agents-are-transforming-data-analytics): Ines Chami, Numbers Station. Ines Chami explains how Numbers Station builds production analytics workflows around LLM agents. The starting problem is self-service analytics: data teams receive requests to find... - [How AI Will Change Gaming Forever](https://mlopstalks.com/talks/how-ai-will-change-gaming-forever): Pietro Gagliano, Transitional Forms. Pietro Gagliano presents projects from Transitional Forms that treat AI as an active part of entertainment production. He describes Agents, a dynamic film in which... - [The Future of AI: Long-Context RAG](https://mlopstalks.com/talks/the-future-of-ai-long-context-rag): Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sophia Skowronski, Breckinridge Capital Advisors & Adam Becker & Binoy Perera, MLOps Community. The paper "Inference Scaling for Long-Context Retrieval Augmented Generation" studies how to allocate long-context inference compute for retrieval-augmented generation. Valdimar Eggertsson explains that the authors... - [AI-Driven Code: Navigating Due Diligence & Transparency in MLOps](https://mlopstalks.com/talks/ai-driven-code-navigating-due-diligence-transparency-in-mlops): Matt van Itallie, Sema. Matt van Itallie explains how Sema evaluates codebases during technical due diligence and for ongoing engineering oversight. The scan covers code quality, development activity, developer... - [Cleric AI SRE: Towards Self-healing Autonomous Software](https://mlopstalks.com/talks/cleric-ai-sre-towards-self-healing-autonomous-software): Willem Pienaar, Cleric. Willem Pienaar describes Cleric as an AI-powered SRE that operates inside a company's production environment. It receives infrastructure events, forms hypotheses, calls existing tools, uses... - [How to Optimize Large AI Models with PyTorch](https://mlopstalks.com/talks/how-to-optimize-large-ai-models-with-pytorch): Michael Gschwind, Meta Platforms. Michael Gschwind describes how his work on accelerators led from game consoles and supercomputers to AI systems. He explains that AI fits accelerators well because... - [LLMs to agents: The Beauty & Perils of Investing in GenAI](https://mlopstalks.com/talks/llms-to-agents-the-beauty-perils-of-investing-in-genai): Sandeep Bakshi, Prosus & Meera Clark, Redpoint Ventures & George Robson, Sequoia Capital. This panel examines where AI agents are useful today and what investors worry about when backing companies built around them. Meera Clark describes agents that... - [Why We Need More Data Science Podcasts](https://mlopstalks.com/talks/why-we-need-more-data-science-podcasts): Hugo Brown Anderson, Delphina. Demetrios Brinkmann, Hugo Brown Anderson, and Duncan discuss why they created the High Signal podcast. Hugo says the show is intended to examine what data... - [RAG: The Future of AI Search (and Prompt Engineering)](https://mlopstalks.com/talks/rag-the-future-of-ai-search-and-prompt-engineering): Korri Jones, Chick-fil-A Corporate Support Center & Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sophia Skowronski, Breckinridge Capital Advisors & Lihu Chen & Binoy Perera. What is the Role of Small Models in the LLM Era: A Survey is the paper discussed in this reading group. Sophia Skowronski uses retrieval-augmented... - [We Can All Be AI Engineers and We Can Do It with Open Source Models](https://mlopstalks.com/talks/we-can-all-be-ai-engineers-and-we-can-do-it-with-open-source-models): Luke Marsden, HelixML. Luke Marsden explains how software engineering practices can apply to generative AI applications. He compares evals with software tests and argues that AI applications should... - [The Coming Revolution of AI Agents](https://mlopstalks.com/talks/the-coming-revolution-of-ai-agents): Jazmia Henry, Iso AI & Rogerio Bonatti, Microsoft & Julia Kroll, Deepgram & Joshua Alphonse, PremAI. The panel examines how AI agents interact through voice, visual interfaces, text, and multiple models. Julia Kroll argues that voice lowers the barrier to using... - [How UX Research Will Shape the Future of AI](https://mlopstalks.com/talks/how-ux-research-will-shape-the-future-of-ai): Lauren Kaplan. Lauren Kaplan describes UX research as learning how people interact with an experience, including their needs, pain points, motivations, and behavior. She explains that the... - [How to Actually Use Cost Effective AI in Your Business](https://mlopstalks.com/talks/how-to-actually-use-cost-effective-ai-in-your-business): Eddie Mattia, Outerbounds & Scott Perry, AWS. The session covers cost-efficient AI infrastructure from workflow orchestration down to custom accelerator hardware. Eddie Mattia walks through an integration between Metaflow and AWS Trainium.... - [Small Models, Big Ideas: The Next Frontier in AI](https://mlopstalks.com/talks/small-models-big-ideas-the-next-frontier-in-ai): Korri Jones, Chick-fil-A Corporate Support Center & Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Sophia Skowronski, Breckinridge Capital Advisors & Lihu Chen, Imperial College London & Binoy Perera, MLOps Community. The paper "What is the Role of Small Models in the LLM Era: A Survey" reviews why small language models still matter alongside large language... - [The EU AI Act: Navigating New Legislation](https://mlopstalks.com/talks/the-eu-ai-act-navigating-new-legislation): Petar Tsankov, LatticeFlow AI. Petar Tsankov describes how AI governance has shifted from abstract fears about AI to the practical work of managing large numbers of deployed applications. Organizations... - [Composable Memory for GPU Optimization](https://mlopstalks.com/talks/composable-memory-for-gpu-optimization): Bernie Wu, MemVerge. Bernie Wu argues that memory has become a central constraint in LLM infrastructure. GPU purchases are often sized around the memory needed by a model,... - [Systematically Test and Evaluate Your LLMs Apps](https://mlopstalks.com/talks/systematically-test-and-evaluate-your-llms-apps): Gideon Mendels, Comet. Gideon Mendels explains how testing changes when an application contains an LLM. Exact string assertions still help with hard rules, but they break when semantically... - [How Agentic Workflows Will Change Everything](https://mlopstalks.com/talks/how-agentic-workflows-will-change-everything): Raj Rikhy, Microsoft. Raj Rikhy explains agents from first principles. An agent is an entity that can act autonomously, make decisions, and use capabilities such as tools or... - [11 lessons learned from doing deployments](https://mlopstalks.com/talks/11-lessons-learned-from-doing-deployments): Sol Rashidi, ExecutiveAI LLC. Sol Rashidi draws on more than 200 POCs and dozens of production products to explain why AI deployments fail after the technology appears promising. Her... - [AI-Powered Data Unification for Data Platforms](https://mlopstalks.com/talks/ai-powered-data-unification-for-data-platforms): Shelby Heinecke, Salesforce. Shelby Heinecke explains how Salesforce uses AI inside its Data Cloud platform. Data arrives from many sources, but ingestion alone is not enough. The platform... - [Building a Data Infrastructure for AI/ML](https://mlopstalks.com/talks/building-a-data-infrastructure-for-ai-ml): Vinoth Chandar, Onehouse. Vinoth Chandar argues that AI and ML projects need a durable data platform underneath them. Models depend on data quality, governance, scale, and careful control... - [Building Hyper-Personalized LLM Applications with Rich Contextual Data](https://mlopstalks.com/talks/building-hyper-personalized-llm-applications-with-rich-contextual-data): Mike Del Balso, Tecton. Mike Del Balso explains why a general-purpose LLM gives generic recommendations when it knows a destination but does not know the user. In his travel... - [Chronon: Airbnb's Open-Source Data Platform](https://mlopstalks.com/talks/chronon-airbnbs-open-source-data-platform): . Nikhil introduces Chronon, an open-source data platform built at Airbnb and Stripe for machine learning and related data use cases. He explains why a simple... - [Common ML Serving Architectures Explained](https://mlopstalks.com/talks/common-ml-serving-architectures-explained): Rebecca Taylor, Lidl e-commerce. Rebecca Taylor explains why model-serving designs in industry often differ from the architectures taught in courses. The available team, approved technology stack, cloud platform, business... - [Data Contracts: The Missing Piece of the Data Puzzle](https://mlopstalks.com/talks/data-contracts-the-missing-piece-of-the-data-puzzle): Mark Freeman, Humu. Mark Freeman explains why data contracts and data observability address different parts of data quality. Observability gives teams broad visibility across pipelines, infrastructure, dependencies, and... - [Data Engineering: The Missing Piece of Your Data Science Puzzle](https://mlopstalks.com/talks/data-engineering-the-missing-piece-of-your-data-science-puzzle): . Aishwarya explains how Chime supports fraud models that need near-real-time inference. She separates features into batch, near-real-time, and real-time categories, then maps each category to... - [Data Quality Management Techniques - The Complete Guide](https://mlopstalks.com/talks/data-quality-management-techniques-the-complete-guide): . Shailvi defines bad data as information that is inaccurate, incomplete, or misleading. Data that produces an unwanted result is not automatically bad if it is... - [Data Scientists & Data Engineers: How the Best Teams Work](https://mlopstalks.com/talks/data-scientists-data-engineers-how-the-best-teams-work): Beverly Wright, Wavicle Data Solutions & Sadie St. Lawrence, Human Machine Collaboration Institute / LinkedIn Learning & Joe Reis, Ternary Data & Victor Cuadros, Microsoft. The panel traces the split between data science and data engineering. Joe Reis describes data engineering as work that originally supported data scientists by building... - [DuckDB is fast for analytics, but what can it do for AI?](https://mlopstalks.com/talks/duckdb-is-fast-for-analytics-but-what-can-it-do-for-ai): Mehdi Ouazza, MotherDuck. Mehdi Ouazza presents DuckDB as a practical component in AI and LLM systems, especially before and after model execution. He starts with DuckDB's embedded design:... - [Engineering Your AI Platform](https://mlopstalks.com/talks/engineering-your-ai-platform): Tobias Macey, Massachusetts Institute of Technology (MIT) & Daniel Svonava, Superlinked & Colleen Tartow, VAST Data. The panel argues that AI platforms should grow from existing data engineering practice instead of becoming a separate stack. Structured and unstructured data need to... - [From Notebook to Kubernetes: Scaling GenAI Pipelines with ZenML](https://mlopstalks.com/talks/from-notebook-to-kubernetes-scaling-genai-pipelines-with-zenml): Alex Strick van Linschoten, ZenML. Alex Strick van Linschoten demonstrates a GenAI workflow that starts in a notebook and moves intensive work to Kubernetes through ZenML. He annotates cat images,... - [GenAI in production with MLflow](https://mlopstalks.com/talks/genai-in-production-with-mlflow): Ben Wilson, Databricks. Ben Wilson explains why moving an agent from a quick demo to production requires more than connecting an application to an LLM API. Agents can... - [How Data Capture Transforms ML Observability](https://mlopstalks.com/talks/how-data-capture-transforms-ml-observability): Pushkar Gar, Clari. Pushkar Gar explains why data capture is the foundation of ML observability. A production ML system can contain production databases, object storage, a data lake,... - [How Feature Stores Work](https://mlopstalks.com/talks/how-feature-stores-work): Simba Khadder, Featureform. Simba Khadder argues that feature engineering is difficult because the clean CSVs used in introductory machine learning do not exist in production. Data scientists often... - [How GPUs are Revolutionizing AI Data Management](https://mlopstalks.com/talks/how-gpus-are-revolutionizing-ai-data-management): . Ryan explains why data curation is necessary when foundation models train on enormous datasets. A curation pipeline starts with raw sources, extracts usable text, applies... - [How To Cut Your Data Infrastructure Costs in Half](https://mlopstalks.com/talks/how-to-cut-your-data-infrastructure-costs-in-half): Jose Navaro, Cleo. Jose Navaro explains how Cleo tracks and reduces data infrastructure costs. He starts with visibility, since cloud-provider dashboards often show which service became more expensive... - [How to Make Your Data Science Reproducible (and Why You Should Care)](https://mlopstalks.com/talks/how-to-make-your-data-science-reproducible-and-why-you-should-care): Ciro Greco, Bauplan. Ciro Greco explains why reproducing a failed data pipeline is harder than reproducing a software failure. A pipeline may have changed code, data, dependencies, or... - [LLMs in Financial Services: Personalized Portfolio Recommendation Engines](https://mlopstalks.com/talks/llms-in-financial-services-personalized-portfolio-recommendation-engines): Akmal Chaudhri. Akmal Chaudhri presents a short notebook-based demo of a chatbot for querying financial data with natural language. A Kafka feed supplies fictitious stock tick data... - [Partnering with Product for Effective, Quality Data Ingestion & Training Data](https://mlopstalks.com/talks/partnering-with-product-for-effective-quality-data-ingestion-training-data): Daniela Santisteban. Daniela Santisteban explains how data engineering teams can work more closely with traditional product managers. Data teams often build pipelines and training data without staying... - [Putting the AI back in Medallion Lake Design](https://mlopstalks.com/talks/putting-the-ai-back-in-medallion-lake-design): Simon Whiteley, Advancing Analytics. Simon Whiteley explains why bronze, silver, and gold are useful shorthand for lakehouse design but poor as rigid architectural rules. Traditional analytics pipelines move from... - [Real-Time Event Processing for AI/ML with Numaflow](https://mlopstalks.com/talks/real-time-event-processing-for-ai-ml-with-numaflow): Sri Harsha Yayi, Intuit. Sri Harsha Yayi introduces Numaflow, an open-source, Kubernetes-native platform from Intuit for real-time event processing and inference. He begins with the problems ML teams face:... - [Scaling Data Reliably: A Journey in Growing Through Data Pain Points](https://mlopstalks.com/talks/scaling-data-reliably-a-journey-in-growing-through-data-pain-points): Miriah Peterson. Miriah Peterson explains data downtime as any period when data is partial, erroneous, or missing. The effects reach beyond broken dashboards. They include inaccurate model... - [Supercharging Your RAG System: Techniques and Challenges](https://mlopstalks.com/talks/supercharging-your-rag-system-techniques-and-challenges): Tengyu Ma, Voyage AI and Stanford University. Tengyu Ma explains why retrieval-augmented generation remains the practical way to give language models access to proprietary company knowledge. He compares RAG with fine-tuning and... - [The Daft distributed Python data engine: multimodal data curation at any scale](https://mlopstalks.com/talks/the-daft-distributed-python-data-engine-multimodal-data-curation-at-any-scale): Jay Chia, eventual. Jay Chia presents Daft as a Python-native data engine for the difficult middle stage of machine learning: turning raw, multimodal data into a usable training... - [The Evolution of Lyft's Feature Store](https://mlopstalks.com/talks/the-evolution-of-lyfts-feature-store): Devon Mittow, Lyft. Devon Mittow describes how Lyft's feature service grew into a mature platform used by machine learning models, marketing, driver incentives, fraud detection, and dispatch. Teams... - [The Future of Data: Composability & the Modular Data Stack](https://mlopstalks.com/talks/the-future-of-data-composability-the-modular-data-stack): Stephen Bailey, Whatnot. Stephen Bailey describes Whatnot's effort to scale its data platform as the company added analytics, machine learning, real-time systems, and application use cases. A simple... - [The Future of Software Architecture for GenAI: Real-Time Data Streaming](https://mlopstalks.com/talks/the-future-of-software-architecture-for-genai-real-time-data-streaming): . The talk uses a fictional airline to explain why batch data pipelines make AI customer support unreliable. A customer may contact the airline through several... - [The Next Revolution in AI: LLMs and Beyond](https://mlopstalks.com/talks/the-next-revolution-in-ai-llms-and-beyond): . Yangqing explains LLMs through the example of Chinese typewriters. Their layouts were optimized by counting which characters appeared together, much like next-token prediction. Modern LLMs... - [The Only Constant is (Data) Change](https://mlopstalks.com/talks/the-only-constant-is-data-change): Benjamin Rogojan, Seattle Data Guy & Chad Sanderson, Gable & Christophe Blefari, NAO & Maggie Hays, Acryl Data. The panel traces how data engineering changed from centrally managed databases and warehouses to cloud systems where many teams can create, transform, and share data.... - [Turn Data Chaos into AI Strategy with Programmatic AI Data Development](https://mlopstalks.com/talks/turn-data-chaos-into-ai-strategy-with-programmatic-ai-data-development): Elena Boiarskaia, Snorkel AI. Elena Boiarskaia argues that enterprise AI teams should treat data development as a software development process. Off-the-shelf models and chatbots often lack the accuracy and... - [Unified Data + AI Governance with Unity Catalog](https://mlopstalks.com/talks/unified-data-ai-governance-with-unity-catalog): Michelle Leon & Victoria Bukta, Databricks. Michelle Leon and Victoria Bukta describe how data platforms become difficult to govern when teams use several catalogs, storage formats, engines, and AI tools. Victoria... - [Why DuckDB is the Future of Data](https://mlopstalks.com/talks/why-duckdb-is-the-future-of-data): Prof. Dr. Hannes Mühleisen, DuckDB Labs. Prof. Dr. Hannes Mühleisen presents DuckDB as an analytical query engine that can run wherever data processing is needed. Its in-process design removes the need... - [Centralized or Decentralized ML Platform?](https://mlopstalks.com/talks/centralized-or-decentralized-ml-platform): Jelmer Borst & Daniela Solis, Picnic. Jelmer Borst and Daniela Solis explain how Picnic organized machine learning as its use cases and model count grew. The company began with forecasting and... - [Making Your Company LLM-native](https://mlopstalks.com/talks/making-your-company-llm-native): Francisco Ingham, Pampa Labs. Francisco Ingham defines an LLM-native company as one that knows how to use LLMs wherever they fit. That includes customer-facing products and the daily workflows... - [Boosting LLMs: Performance, Scaling, and Structured Outputs](https://mlopstalks.com/talks/boosting-llms-performance-scaling-and-structured-outputs): Tom Sabo, SAS & Matt Squire, Fuzzy Labs & Vaibhav Gupta, Boundary ML. This session contains three talks about making LLM systems more useful in production. Matt Squire presents a self-hosted documentation assistant using RAG, guardrails, Mistral 7B... - [Unpacking 3 Types of Feature Stores](https://mlopstalks.com/talks/unpacking-3-types-of-feature-stores): Simba Khadder, Featureform. Simba Khadder explains how his work on recommender systems led him to embeddings and feature stores. Embeddings can represent users, items, images, and other objects,... - [Integrating Knowledge Graphs & Vector RAG for Efficient Information Extraction](https://mlopstalks.com/talks/integrating-knowledge-graphs-and-vector-rag-for-efficient-information-extraction): Nehil Jain, Stealth AI Startup & Sonam Gupta, AICamp & Matt Squire & Valdimar Eggertsson, Snjallgögn (Smart Data inc.) & Binoy Perera, MLOps Community. The paper "HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction" combines vector retrieval with a knowledge graph built from financial... - [Reinvent Yourself and Be Curious](https://mlopstalks.com/talks/reinvent-yourself-and-be-curious): Stefano Bosisio, Synthesia. Stefano Bosisio describes a career that moved from biomedical engineering to a chemistry PhD, then data science in banking, and finally ML platform engineering. His... - [Global Feature Store: Optimizing Locally and Scaling Globally at Delivery Hero](https://mlopstalks.com/talks/global-feature-store-optimizing-locally-and-scaling-globally-at-delivery-hero): Gottam Sai Bharath & Cole Bailey, Delivery Hero. Gottam Sai Bharath and Cole Bailey describe how Delivery Hero changed its approach to machine learning platform work. A central team initially tried to build... - [RAG Quality Starts with Data Quality](https://mlopstalks.com/talks/rag-quality-starts-with-data-quality): Adam Kamor, Tonic.ai. Adam Kamor explains why RAG projects often fail before retrieval begins. The source documents need to be extracted correctly, converted into a usable structure, chunked... - [Who's MLOps for Anyway?](https://mlopstalks.com/talks/whos-mlops-for-anyway): Jonathan Rioux, EPAM Systems. Jonathan Rioux argues that MLOps is a set of principles, processes, and tools for moving an idea into production and maintaining it. It does not... - [Alignment is Real](https://mlopstalks.com/talks/alignment-is-real): Shiva Bhattacharjee, TrueLaw Inc. Shiva Bhattacharjee explains how TrueLaw builds AI systems for lawyers, where precision matters more than instant responses and users are not usually prompt engineers. The... - [Ax a New Way to Build Complex Workflows with LLMs](https://mlopstalks.com/talks/ax-a-new-way-to-build-complex-workflows-with-llms): Vikram Rangnekar, Stealth. Vikram Rangnekar explains why he built Ax, a TypeScript framework for composing LLM workflows. He began with a project called 42 Papers, where small models... - [Visualize - Bringing Structure to Unstructured Data](https://mlopstalks.com/talks/visualize-bringing-structure-to-unstructured-data): Markus Stoll, Renumics. Markus Stoll explains how Renumics uses embeddings and visualization to make large, messy ML datasets easier to inspect. He prefers two-dimensional UMAP maps because they... - [MLSecOps is Fundamental to Robust AI Security Posture Management](https://mlopstalks.com/talks/mlsecops-is-fundamental-to-robust-ai-security-posture-management): Sean Morgan, Protect AI. Sean Morgan explains why machine learning teams need MLSecOps, which applies security practices throughout the AI and machine learning lifecycle. The risks include poisoned training... - [MLOps for GenAI Applications](https://mlopstalks.com/talks/mlops-for-genai-applications): Harcharan Kabbay, World Wide Technology. Harcharan Kabbay explains how to move GenAI applications from experiments into managed services. He treats a RAG system as several connected components, including retrieval, vector... - [Exploring Long Context Language Models](https://mlopstalks.com/talks/exploring-long-context-language-models): Nehil Jain, Stealth AI Startup & Sonam Gupta, AICamp & Korri Jones, Chick-fil-A Corporate Support Center & Binoy Perera, MLOps Community. Can Long-context Language Models Subsume Retrieval, RAG, SQL, and More? is the paper discussed in this reading group. Sonam Gupta introduces long-context language models and... - [BigQuery Feature Store](https://mlopstalks.com/talks/bigquery-feature-store): Nicolas Mauti, Malt. Nicolas Mauti explains why Malt built a feature store with BigQuery for its recommendation, NLP, and matching models. Previously, data scientists computed features inside training... - [Design and Development Principles for LLMOps](https://mlopstalks.com/talks/design-and-development-principles-for-llmops): Andy McMahon, Barclays Bank. Andy McMahon argues that LLMOps should extend established software and MLOps practices rather than replace them. Teams still need requirements, development stages, testing, validation, deployment,... - [Data Quality = Quality AI](https://mlopstalks.com/talks/data-quality-quality-ai): Samuel Partee, Redis & Chad Sanderson, Gable & Joe Reis, Ternary Data & Maria Zhang, Proactive AI Lab Inc & Pushkar Garg, Clari Inc. The panel defines data quality as a set of measurable properties that need continuous monitoring. Maria Zhang names completeness, accuracy, validity, and timeliness. Pushkar Garg... - [The Variational Book](https://mlopstalks.com/talks/the-variational-book): Yuri Plotkin, ML Scientist. Yuri Plotkin discusses how he moved from biomedical engineering and wet-lab research into computer science and generative AI. His book, The Variational Book, grew from... - [Vision and Strategies for Attracting & Driving AI Talents in High Growth](https://mlopstalks.com/talks/vision-and-strategies-for-attracting-driving-ai-talents-in-high-growth): Ashley Antonides, Two Six Technologies & Olga Beregovaya, Smartling & Shailvi Wakhlu, Shailvi Ventures LLC. This panel focuses on the people systems behind growing AI teams. Olga Beregovaya, Ashley Antonides, and Shailvi Wakhlu discuss how to retain technical staff through... - [Harnessing AI APIs for Safer, Accurate, & Reliable Applications](https://mlopstalks.com/talks/harnessing-ai-apis-for-safer-accurate-reliable-applications): Ron Heichman, SentinelOne. Ron Heichman explains why reliable LLM applications depend on understanding and testing the context sent to a model. Agent frameworks may include retrieval, vector stores,... - [Balancing Speed and Safety](https://mlopstalks.com/talks/balancing-speed-and-safety): Remy Thellier, Vectice & Erica Greene, Yahoo & Shreya Rajpal, Guardrails AI. This panel treats AI safety as a product and company risk question rather than a distant discussion about machines taking over the world. Erica Greene... - [Reliable LLM Products, Fueled by Feedback](https://mlopstalks.com/talks/reliable-llm-products-fueled-by-feedback): Chinar Movsisyan, Feedback Intelligence. Chinar Movsisyan describes a gap between building an AI model and understanding how people experience the resulting product. Standard evaluation metrics such as accuracy, recall,... - [A Blueprint for Scalable & Reliable Enterprise AI/ML Systems](https://mlopstalks.com/talks/a-blueprint-for-scalable-reliable-enterprise-ai-ml-systems): Hira Dangol, Bank of America & Rama Akkiraju, NVIDIA & Nitin Aggarwal, Google & Steven Eliuk, IBM. This panel gives a practical view of what enterprise AI systems need after the prototype stage. Rama Akkiraju says teams should define the business outcome... - [AI Operations Without Fundamental Engineering Discipline](https://mlopstalks.com/talks/ai-operations-without-fundamental-engineering-discipline): Nikhil Suresh, Hermit Tech. Nikhil Suresh argues that many AI initiatives begin before a company has defined the decision the system will support, the action someone will take, or... - [AI in Healthcare](https://mlopstalks.com/talks/ai-in-healthcare): Eric Landry, Zeteo Health. Eric Landry describes the practical limits of building AI for healthcare. He compares his early NLP work in 2005, when computation and memory made experiments... - [Evaluating the Effectiveness of Large Language Models](https://mlopstalks.com/talks/evaluating-the-effectiveness-of-large-language-models): Aniket Singh, Ultium Cells. Aniket Singh explains an approach to evaluating LLM capability through tasks that resemble human decision-making. His research includes simulated auction bidding, where models receive personalities... - [Extending AI: From Industry to Innovation](https://mlopstalks.com/talks/extending-ai-from-industry-to-innovation): Sophia Rowland & David Weik, SAS. Sophia Rowland and David Weik describe the practical problems they see when organizations move models into production. Traditional MLOps work now includes real-time fraud decisions,... - [AI For Good - Detecting Harmful Content at Scale](https://mlopstalks.com/talks/ai-for-good-detecting-harmful-content-at-scale): Matar Haller, ActiveFence. Matar Haller explains how ActiveFence helps online platforms detect harmful content without making the moderation decision for them. Its API accepts text, images, audio, and... - [All Data Scientists Should Learn Software Engineering Principles](https://mlopstalks.com/talks/all-data-scientists-should-learn-software-engineering-principles): Catherine Nelson, Freelance Data Scientist. Catherine Nelson argues that data scientists need software engineering skills because exploratory work increasingly becomes part of production systems. She explains that notebooks and quick... - [AI Agents for Consumers](https://mlopstalks.com/talks/ai-agents-for-consumers): Shaun Wei, RealChar. Shaun Wei describes Rivia, RealChar's consumer assistant for handling routine phone calls. The product is intended to call customer service lines, press keypad buttons, receive... - [ML and AI as Distinct Control Systems in Heavy Industrial Settings](https://mlopstalks.com/talks/ml-and-ai-as-distinct-control-systems-in-heavy-industrial-settings): Richard Howes, Metaformed. Richard Howes describes how oil and gas, forestry, manufacturing, and other heavy industries use ML and AI around equipment, compliance, documents, imagery, and operational data.... - [Accelerating Multimodal AI](https://mlopstalks.com/talks/accelerating-multimodal-ai): Ethan Rosenthal, Runway. Ethan Rosenthal describes the infrastructure problems he sees while moving from tabular machine learning and language models to generative video at Runway. His main proposal... - [Fresh Data, Smart Retrieval: Milvus & Jina CLIP Explained](https://mlopstalks.com/talks/fresh-data-smart-retrieval-milvus-jina-clip-explained): Stephen Batifol, Zilliz & Andreas Koukounas & Saba Sturua, Jina AI. Stephen Batifol explains why updating a RAG system needs more planning than inserting documents once. In Milvus, stable identifiers let an upsert replace an existing... - [Navigating the AI Frontier: The Power of Synthetic Data and Agent Evaluations in LLM Development](https://mlopstalks.com/talks/navigating-the-ai-frontier-the-power-of-synthetic-data-and-agent-evaluations-in): Boris Selitser, Okareo. Boris Selitser describes how LLM application development is bringing software engineering and machine learning closer together. Foundation models shorten experimentation cycles, while production quality still... - [How to Build Production-Ready AI Models for Manufacturing](https://mlopstalks.com/talks/how-to-build-production-ready-ai-models-for-manufacturing): Pavol Bielik, LatticeFlow & Aniket Singh & Mohan Mahadevan & Jürgen Weichenberger, Schneider Electric. The panel describes the practical conditions that make manufacturing AI different from a standard machine learning project. Applications range from battery and semiconductor inspection to... - [From Robotics to Recommender Systems](https://mlopstalks.com/talks/from-robotics-to-recommender-systems): Miguel Fierro, Microsoft. Miguel Fierro compares machine learning with the physics-based methods used in robotics. Boston Dynamics, he says, built much of its earlier work around equations of... - [Uber's Michelangelo: Strategic AI Overhaul and Impact](https://mlopstalks.com/talks/ubers-michelangelo-strategic-ai-overhaul-and-impact): . Demetrios Brinkmann breaks down Uber's account of Michelangelo, its internal machine learning platform. The platform began in 2016 because teams were building models and production... - [AWS Trainium and Inferentia](https://mlopstalks.com/talks/aws-trainium-and-inferentia): Kamran Khan, Annapurna ML & Matthew McClean, AWS, Annapurna Labs. Matthew McClean and Kamran Khan explain why AWS built Trainium and Inferentia instead of relying only on GPUs. Their chips target deep learning operations such... - [Build Reliable Systems with Chaos Engineering](https://mlopstalks.com/talks/build-reliable-systems-with-chaos-engineering): Benjamin Wilms, Steadybit. Benjamin Wilms describes chaos engineering as a way to train systems, teams, and organizations for stressful conditions such as latency spikes, network failures, cloud outages,... - [Managing Small Knowledge Graphs for Multi-agent Systems](https://mlopstalks.com/talks/managing-small-knowledge-graphs-for-multi-agent-systems): Tom Smoker, WhyHow.ai. Tom Smoker explains why WhyHow.ai uses knowledge graphs alongside vector and relational databases in RAG systems. His focus is reliability in high-value settings where an... - [Just when we Started to Solve Software Docs, AI Blew Everything Up](https://mlopstalks.com/talks/just-when-we-started-to-solve-software-docs-ai-blew-everything-up): Dave Nunez, Abstract Group. Dave Nunez explains how documentation affects a developer before they have learned a product's terminology. A page with a clear starting point, whitespace, diagrams, short... - [Evaluating Quality and Improving LLM Products at Scale](https://mlopstalks.com/talks/evaluating-quality-and-improving-llm-products-at-scale): Austin Bell, Slack. Austin Bell explains how Slack evaluates generative AI products such as channel and thread summarization and natural-language search. The central problem is that each user... - [Navigating the Emerging LLMOps Stack](https://mlopstalks.com/talks/navigating-the-emerging-llmops-stack): Hien Luu, DoorDash. Hien Luu shares lessons from exploring an LLMOps stack strategy for DoorDash. He starts with the practical challenges of deploying language-model applications, including inference, serving,... - [Product Thinking in Data & AI](https://mlopstalks.com/talks/product-thinking-in-data-ai): Stuart Winter-Tear. Stuart Winter-Tear argues that AI projects often fail to produce value because teams start with what they can build instead of the problem they need... - [Beyond Guess-and-Check: Towards AI-assisted Prompt Engineering](https://mlopstalks.com/talks/beyond-guess-and-check-towards-ai-assisted-prompt-engineering): Alex Cabrera, Carnegie Mellon University. Alex Cabrera argues that prompt engineering still depends too much on guess-and-check. Developers write a prompt, try it on a few examples, inspect the output,... - [Evaluating Language Models](https://mlopstalks.com/talks/evaluating-language-models): Matthew Sharp, LTK. Matthew Sharp argues that language model evaluation has become too focused on easy-to-compare benchmark scores. Most popular benchmarks use multiple-choice questions or standardized tests, even... - [Ghostwriter - AI Writing That Learns From You](https://mlopstalks.com/talks/ghostwriter-ai-writing-that-learns-from-you): Jonny Dimond, Shortwave. Jonny Dimond explains how Shortwave built Ghostwriter, an AI writing system for email that learns from a user's own messages. The system embeds incoming emails,... - [Let's Build a Website in 10 Minutes with GitHub Copilot](https://mlopstalks.com/talks/lets-build-a-website-in-10-minutes-with-github-copilot): Bryant Son, GitHub. Bryant Son gives a short introduction to GitHub Copilot and then demonstrates it in Visual Studio Code. He describes Copilot as an AI code-completion tool... - [No GPU Before PMF](https://mlopstalks.com/talks/no-gpu-before-pmf): Stanislas Polu, Dust. Stanislas Polu argues that early AI startups should be careful about where they spend technical effort. B2C products handle large volumes, so they usually optimize... - [The Intersection of Graphs and Large Language Models](https://mlopstalks.com/talks/the-intersection-of-graphs-and-large-language-models): Anthony Alcaraz, Fribl. Anthony Alcaraz presents knowledge graphs as the foundation for retrieval-augmented generation systems that need to reason over business data. He argues that RAG should be... - [Open Standards Make MLOps Easier and Silos Harder](https://mlopstalks.com/talks/open-standards-make-mlops-easier-and-silos-harder): Cody Peterson, Voltron Data. Cody Peterson argues that MLOps depends heavily on the data layer, where teams still face problems with data versioning, cleaning, access, audits, scale, and handoffs... - [Retrieval Augmented Generation](https://mlopstalks.com/talks/retrieval-augmented-generation): Syed Asad, KiwiTech. Syed Asad discusses the practical problems he has encountered while building and deploying RAG systems under tight client deadlines. A 133 MB agricultural CSV defeated... - [Building AI Products across Multiple Domains: Commonalities & Non-Commonalities](https://mlopstalks.com/talks/building-ai-products-across-multiple-domains-commonalities-non-commonalities): Dhruv Ghulati. Dhruv Ghulati compares AI product management across document extraction, fraud detection, natural language understanding, recommender systems, marketplace optimization, and assistants. He says AI product managers... - [Productionizing AI: How to Think From the End](https://mlopstalks.com/talks/productionizing-ai-how-to-think-from-the-end): Annie Condon. Annie Condon argues that teams should start with the experience they want users to have and work backward into the AI system. She illustrates this... - [RecSys at Spotify](https://mlopstalks.com/talks/recsys-at-spotify): Sanket Gupta, Spotify. Sanket Gupta explains how Spotify builds recommendation systems around user and item embeddings. A track embedding combines audio characteristics such as tempo, pitch, instrumentation, and... - [From A Coding Startup to AI Development in the Enterprise](https://mlopstalks.com/talks/from-a-coding-startup-to-ai-development-in-the-enterprise): Ryan Carson, Intel. Ryan Carson describes how his experience building Treehouse led him toward Intel and AI development. Treehouse began with a simple goal: give people a trusted,... - [AI Innovations: The Power of Feature Platforms](https://mlopstalks.com/talks/ai-innovations-the-power-of-feature-platforms): Mahesh Murag, Tecton & Jose Navarro, Cleo & Nikhil Garg, Fennel. This session covers three approaches to building feature platforms. Mahesh Murag explains Tecton's unified interface for defining, computing, and retrieving features in Python, with offline... - [FedML Nexus AI: Your Generative AI Platform at Scale](https://mlopstalks.com/talks/fedml-nexus-ai-your-generative-ai-platform-at-scale): Salman Avestimehr, FedML. Salman Avestimehr describes FedML as a platform for teams that want to build and operate generative AI applications without giving up control to a hosted... - [What is AI Quality?](https://mlopstalks.com/talks/what-is-ai-quality): Mohamed Elgendy, Kolena Inc.. Mohamed Elgendy defines AI quality through two questions: does the product perform the function it was built for, and are its risks understood and controlled?... - [Data Labeling Best Practices](https://mlopstalks.com/talks/data-labeling-best-practices): Charles Brecque, TextMine. Charles Brecque describes the data labeling process TextMine developed while fine-tuning models for extracting information from business documents. He explains when labeling is useful, especially... - [Explaining ChatGPT to Anyone in 10 Minutes](https://mlopstalks.com/talks/explaining-chatgpt-to-anyone-in-10-minutes): Cameron Wolfe, Rebuy. Cameron Wolfe gives a short technical explanation of why ChatGPT works better than earlier language models. His framework has three parts. Transformers process a sequence... - [LLMOps and GenAI at Enterprise Scale - Challenges and Opportunities](https://mlopstalks.com/talks/llmops-and-genai-at-enterprise-scale-challenges-and-opportunities): Andy McMahon, NatWest Group. Andy McMahon argues that deploying LLM and GenAI systems at enterprise scale is difficult because organizations are still moving from experimentation into development and production.... - [Streamlining Model Deployment](https://mlopstalks.com/talks/streamlining-model-deployment): Daniel Lenton, Unify. Daniel Lenton argues that deploying AI models has become difficult because the number of endpoints, models, serving systems, compression methods, compilers, and hardware options keeps... - [Handling Multi-Terabyte LLM Checkpoints](https://mlopstalks.com/talks/handling-multi-terabyte-llm-checkpoints): Simon Karasik, Nebius AI. Simon Karasik explains what changes when machine learning infrastructure moves from traditional models to large language models. He describes training a 300-billion-parameter model on more... - [Leading Enterprise Data Teams](https://mlopstalks.com/talks/leading-enterprise-data-teams): Sol Rashidi, ExecutiveAI. Sol Rashidi explains how she leads large enterprise data and AI teams, especially when projects, ownership, and priorities are unclear. She rejects business value as... - [Building Conversational AI Agents with Voice](https://mlopstalks.com/talks/building-conversational-ai-agents-with-voice): Michelle Chan, Deepgram. Michelle Chan explains how to build voice agents that feel more like conversations between people. She describes the basic pipeline: speech is transcribed, sent to... - [Reliable Hallucination Detection in Large Language Models](https://mlopstalks.com/talks/reliable-hallucination-detection-in-large-language-models): Jiaxin Zhang, Intuit AI Research. Jiaxin Zhang explains why hallucination detection matters for products such as Intuit's financial assistants, where incorrect answers can damage trust. He reviews factuality hallucinations, where... - [DSPy Assertions: Computational Constraints for Self-Refining LM Pipelines](https://mlopstalks.com/talks/dspy-assertions-computational-constraints-for-self-refining-lm-pipelines): Arnav Singhvi, DSPy. Arnav Singhvi presents DSPy as a way to program language models through reusable signatures, modules, and optimizers instead of maintaining long prompt templates. A DSPy... - [Shipping LLMs: Buckle Up & Enjoy the Ride](https://mlopstalks.com/talks/shipping-llms-buckle-up-enjoy-the-ride): Rex Harris. Rex Harris frames LLM work as a progression from prompt experiments to proof-of-concept applications and then production systems. His advice starts with finding a real... - [The Rise of Modern Data Management](https://mlopstalks.com/talks/the-rise-of-modern-data-management): Chad Sanderson, Gable.ai. Chad Sanderson argues that data infrastructure is changing because companies are demanding a clearer link between data and business value. Analytics pipelines built around Snowflake,... - [Lessons from Building LLM-based Social Media Products](https://mlopstalks.com/talks/lessons-from-building-llm-based-social-media-products): Faizaan Charania, LinkedIn. Faizaan Charania describes how he and his teams brought generative AI features to LinkedIn users. He starts with product discovery: talk to users, test assumptions,... - [Making Sense of LLMOps](https://mlopstalks.com/talks/making-sense-of-llmops): Maria Vechtomova, Ahold Delhaize & Başak Tuğçe Eskili, Booking.com. Maria Vechtomova and Başak Tuğçe Eskili explain how teams can decide whether an LLM application makes sense and how to operate it responsibly. They describe... - [Beyond AGI, Can AI Help Save the Planet?](https://mlopstalks.com/talks/beyond-agi-can-ai-help-save-the-planet): Patrick Beukema, Allen Institute for Artificial Intelligence (AI2). Patrick Beukema leads the Environmental AI team at AI2, where the work focuses on conservation and sustainability rather than commercial model development. He describes projects... - [Enabling Efficient Trillion Parameter Scale Training for Deep Learning Models](https://mlopstalks.com/talks/enabling-efficient-trillion-parameter-scale-training-for-deep-learning-models): Tunji Ruwase, Microsoft. Tunji Ruwase explains how DeepSpeed addresses three limits in large-model training: memory, compute, and data. ZeRO partitions optimizer states, gradients, and parameters across GPUs instead... - [GenAI in Production - Challenges and Trends](https://mlopstalks.com/talks/genai-in-production-challenges-and-trends): Verena Weber, Verena Weber. Verena Weber discusses how AI systems move from experiments into production, drawing on her work as a data scientist, consultant, and research scientist on Amazon... - [Graphs and Language](https://mlopstalks.com/talks/graphs-and-language): Louis Guitton. Louis Guitton explains how knowledge graphs and language models can support each other. A graph can ground an answer in explicit facts, while a language... - [Innovative Gen AI Applications: Beyond Text](https://mlopstalks.com/talks/innovative-gen-ai-applications-beyond-text): Diana C. Montañes Mondragon & Nick Schenone, QuantumBlack. Diana C. Montañes Mondragon discusses generative AI for molecule discovery. She explains how molecules can be represented as strings or graphs, then used with chemical... - [From Robotics to AI NPCs](https://mlopstalks.com/talks/from-robotics-to-ai-npcs): Nyla Worker, Convai. Nyla Worker compares robots with embodied AI NPCs in games. Robots start with physical hardware, then need systems for localization, mapping, perception, planning, control, and... - [Seeing Like a Language Model](https://mlopstalks.com/talks/seeing-like-a-language-model): Linus Lee, Notion. Linus Lee argues that language models may be easier to work with when represented through the features they learn internally, rather than through tokens alone.... - [Introducing DBRX: The Future of Language Models](https://mlopstalks.com/talks/introducing-dbrx-the-future-of-language-models): Davis Blalock, Bandish Shah, Abhi Venigalla & Ajay Saini, Databricks. This roundtable explains how Databricks built and trained DBRX. The team moved from dense models toward a mixture-of-experts design, giving the model more parameters while... - [Fine Tuning Llamas](https://mlopstalks.com/talks/fine-tuning-llamas): Kai Davenport. Kai Davenport gives a short overview of Helix, a platform built with Luke for running and fine-tuning open-source AI models. The service accepts PDFs, Word... - [Productionizing Health Insurance Appeal Generation](https://mlopstalks.com/talks/productionizing-health-insurance-appeal-generation): Holden Karau, Netflix. Holden Karau describes a personal project to generate health insurance appeals. Her starting point is the difficulty of obtaining training data. Insurance companies have little... - [From MVP to Production](https://mlopstalks.com/talks/from-mvp-to-production): Eric Peter, Databricks & Donné Stevenson & Phillip Carter, Honeycomb & Andrew Hoh, Last Mile AI. The panel focuses on the work that begins after an AI demo appears to function. Phillip Carter says production users quickly expose behavior that internal... - [Building a Python-Centric Feature Platform to Power Production AI Applications](https://mlopstalks.com/talks/building-a-python-centric-feature-platform-to-power-production-ai-applications): Matt Bleifer, Tecton. Matt Bleifer explains how Tecton built a feature platform around the different needs of data scientists and software engineers. Data scientists want Python, notebooks, quick... - [Graduating from Proprietary to Open Source Models in Production](https://mlopstalks.com/talks/graduating-from-proprietary-to-open-source-models-in-production): Philip Kiely, Baseten. Philip Kiely explains why teams may move from hosted proprietary model endpoints to open source models that they can run and control themselves. He defines... - [RagSys: RAG is just RecSys in Disguise](https://mlopstalks.com/talks/ragsys-rag-is-just-recsys-in-disguise): Chang She, LanceDB. Chang She argues that production RAG has more in common with recommender systems than many teams acknowledge. A RAG pipeline experiments with chunking, embedding models,... - [Data Engineering in the Federal Sector](https://mlopstalks.com/talks/data-engineering-in-the-federal-sector): Shane Morris, Devis. Shane Morris discusses his path from music management into data engineering, federal contracting, and advising technology companies. His music work involved analytics, digital assets, cloud... - [Charting LLMOps Odyssey](https://mlopstalks.com/talks/charting-llmops-odyssey): Yinxi Zhang, Databricks. Yinxi Zhang explains how LLM application development extends familiar MLOps practices. She begins with business understanding, data analysis, prototyping, packaging, evaluation, CI/CD, and serving. The... - [From Research to Production: Fine-Tuning & Aligning LLMs](https://mlopstalks.com/talks/from-research-to-production-fine-tuning-aligning-llms): Philipp Schmid, Hugging Face. Philipp Schmid explains how teams can take open LLMs from research into production by fine-tuning them for a specific task and aligning their behavior. He... - [Navigating via Retrieval Evaluation to Demystify LLM Wonderland](https://mlopstalks.com/talks/navigating-via-retrieval-evaluation-to-demystify-llm-wonderland): Atita Arora, Qdrant. Atita Arora argues that retrieval deserves close attention in LLM applications because RAG systems depend on the information they retrieve before a model generates an... - [The State of Production Machine Learning in 2024](https://mlopstalks.com/talks/the-state-of-production-machine-learning-in-2024): Alejandro Saucedo, Zalando SE. Alejandro Saucedo describes production machine learning as a system that begins, rather than ends, when a model is trained and deployed. Production adds specialized hardware,... - [Vision Pipelines in Production: Serving & Optimisations](https://mlopstalks.com/talks/vision-pipelines-in-production-serving-optimisations): Biswaroop Bhattacharjee, Prem AI. Biswaroop Bhattacharjee explains how to move a constrained image-generation system from experimentation toward production. His example generates realistic planet images with fixed composition, configurable visual... - [What Business Stakeholders Want to See from the ML Teams](https://mlopstalks.com/talks/what-business-stakeholders-want-to-see-from-the-ml-teams): Peter Guagenti, Tabnine. Peter Guagenti discusses how technical teams and business stakeholders can work together on data products, machine learning, and AI tools. He argues that teams often... - [Designing ML Infra for ML & LLM Use Cases](https://mlopstalks.com/talks/designing-ml-infra-for-ml-llm-use-cases): Amritha Arun Babu, Klaviyo & Abhik Choudhury, IBM. Abhik Choudhury describes MLOps maturity as a progression from manual work to standardized experimentation, packaged pipelines, model registries, continuous monitoring, and automated responses. He says... - [Anatomy of a Software 3.0 Company](https://mlopstalks.com/talks/anatomy-of-a-software-3-0-company): Sarah Guo, Conviction. Sarah Guo presents Conviction's framework for evaluating AI-native companies. She describes Software 3.0 as systems that manipulate foundation models to create useful products. The opportunity... - [Building the Next Generation of Reliable AI](https://mlopstalks.com/talks/building-the-next-generation-of-reliable-ai): Shreya Rajpal, Guardrails AI. Shreya Rajpal explains what has made generative AI difficult for enterprises to adopt in production. Companies need systems that solve a narrow business problem consistently,... - [4 Years of the MLOps Community](https://mlopstalks.com/talks/4-years-of-the-mlops-community): Demetrios Brinkmann, MLOps Community. Mihail Eric talks with Demetrios Brinkmann about how the MLOps Community began and what it became after four years. The community started during the COVID-19... - [The Art and Science of Training LLMs](https://mlopstalks.com/talks/the-art-and-science-of-training-llms): Bandish Shah & Davis Blalock, MosaicML/Databricks. Davis Blalock and Bandish Shah describe LLM training as a system with failure points at every layer. GPUs can fail silently, distributed communication can time... - [Security and Privacy](https://mlopstalks.com/talks/security-and-privacy): Ads Dawson, Kaseya & Katharine Jarmul, Thoughtworks & David Haber, Lira. This panel separates privacy from security and then connects both to the practical work of deploying LLM systems. Katharine Jarmul explains that privacy has legal... - [Model Merging and Mixtures of Experts](https://mlopstalks.com/talks/model-merging-and-mixtures-of-experts): Maxime Labonne, J.P. Morgan. Maxime Labonne explains why model merging has become common in the open-source LLM community. He covers SLERP, TIES, passthrough merging, and Franken-merging, then describes a... - [Why Purpose-built Vector Databases Matter for Your Use Case](https://mlopstalks.com/talks/why-purpose-built-vector-databases-matter-for-your-use-case): Frank Liu, Jiang Chen & Yujian Tang, Zilliz. Demetrios Brinkmann hosts Frank Liu, Jiang Chen, and Yujian Tang in a discussion about when teams should use a purpose-built vector database instead of adding... - [A Decade of AI Safety and Trust](https://mlopstalks.com/talks/a-decade-of-ai-safety-and-trust): Petar Tsankov, LatticeFlow AI. Petar Tsankov describes how AI safety grew out of a decade of research focused on model robustness and reliability. Earlier machine learning work optimized accuracy... - [The Real E2E RAG Stack](https://mlopstalks.com/talks/the-real-e2e-rag-stack): Sam Bean, Rewind.ai. Sam Bean discusses the operational problems behind search, LLM applications, and production RAG. Search has many failure modes because a query may have no answer,... - [Managing Data for Effective GenAI Application](https://mlopstalks.com/talks/managing-data-for-effective-genai-application): Anu Arora & Anass Bensrhir, QuantumBlack AI by McKinsey. Anu Arora and Anass Bensrhir explain why data engineering remains difficult as companies adopt GenAI. Traditional data systems already had methods for measuring quality, building... - [Becoming an AI Evangelist](https://mlopstalks.com/talks/becoming-an-ai-evangelist): Alex Volkov, Weights & Biases. Alex Volkov describes how a long career in generalist software engineering led him into AI evangelism. DALL-E, Stable Diffusion, and Whisper pulled him into model... - [A Survey of Production RAG Pain Points and Solutions](https://mlopstalks.com/talks/a-survey-of-production-rag-pain-points-and-solutions): Jerry Liu, LlamaIndex. Jerry Liu explains why a five-line RAG prototype becomes difficult to operate in production. Simple retrieval works for a fact in one document, but quality... - [LLM Use Cases in Production](https://mlopstalks.com/talks/llm-use-cases-in-production): Agnieszka Mikołajczyk-Bareła, Chaptr & Jason Liu & Arjun Kannan, Resides. This panel focuses on the difference between an LLM capability and the value created around it. Arjun Kannan describes using property documents, including posters, PDFs,... - [Information Retrieval & Relevance](https://mlopstalks.com/talks/information-retrieval-relevance): Daniel Svonava, Superlinked. Daniel Svonava explains why Superlinked moved from recommender systems toward infrastructure for information retrieval. The company's approach builds vectors from complex, mixed data such as... - [Evaluating and Integrating ML Models](https://mlopstalks.com/talks/evaluating-and-integrating-ml-models): Morgan McGuire & Anish Shah, Weights & Biases. Anish Shah and Morgan McGuire describe their work on the growth team at Weights & Biases, which combines machine learning engineering, user support, education, integrations,... - [Data Governance and AI](https://mlopstalks.com/talks/data-governance-and-ai): Alexandra Diem, Gjensidige. Alexandra Diem describes how she moved from applied mathematics and biomedical research into consulting and then into her role leading cloud analytics and MLOps at... - [Ads Ranking Evolution at Pinterest](https://mlopstalks.com/talks/ads-ranking-evolution-at-pinterest): Aayush Mudgal, Pinterest. Aayush Mudgal walks through Pinterest's ads ranking work from 2018 through 2024. He explains how the team moved from basic impression and click optimization toward... - [LLM Evaluation with Arize AI's Aparna Dhinakaran](https://mlopstalks.com/talks/llm-evaluation-with-arize-ais-aparna-dhinakaran): Arize AI's Aparna Dhinakaran. Aparna Dhinakaran explains why evaluating an LLM application is different from evaluating a base model. Teams care about whether a particular prompt, retrieval setup, and... - [Lightweight Feature Platform](https://mlopstalks.com/talks/lightweight-feature-platform): Matt Bleifer & Mike Eastham, Tecton. Matt Bleifer and Mike Eastham describe how Tecton evolved from a feature store into a broader feature platform. The system helps teams define features, build... - [Gen AI Buy vs Build, Commercial vs Open Source](https://mlopstalks.com/talks/gen-ai-buy-vs-build-commercial-vs-open-source): Ilona Logvinova, McKinsey & Mohamed Abusaid, QuantumBlack, AI by McKinsey & Nayur Khan, Goldman Sachs. The panel separates several decisions that are often mixed together. An organization might buy a product with an embedded model, build a custom application around... - [Micro Graph Transformer Powering Small Language Models](https://mlopstalks.com/talks/micro-graph-transformer-powering-small-language-models): Jon Cooke, Dataception. Jon Cooke argues that data and analytics projects take too long because organizations start with platforms, schemas, and data requests instead of the business decision... - [How Data Platforms Affect ML & AI](https://mlopstalks.com/talks/how-data-platforms-affect-ml-ai): Jake Watson, The Oakland Group. Jake Watson explains how data platforms support machine learning and AI work. He describes platforms as systems that can be as small as a database... - [RAG Has Been Oversimplified](https://mlopstalks.com/talks/rag-has-been-oversimplified): Yujian Tang, Zilliz. Yujian Tang explains why the standard RAG diagram hides important engineering choices. An application usually combines an embedding model, a vector database, and a language... - [The Myth of AI Breakthroughs](https://mlopstalks.com/talks/the-myth-of-ai-breakthroughs): Jonathan Frankle, Databricks. Jonathan Frankle argues that AI progress is usually slower and less tidy than online hype suggests. His research team tests papers and training methods against... - [MLOps at the Crossroads](https://mlopstalks.com/talks/mlops-at-the-crossroads): Patrick Barker, Kentauros AI & Farhood Etaati, AIMedic. Patrick Barker and Farhood Etaati disagree about whether LLMOps deserves to be treated as a separate field. Barker says LLM applications bring a new group... - [Pioneering AI Models for Regional Languages](https://mlopstalks.com/talks/pioneering-ai-models-for-regional-languages): Aleksa Gordić, OrtusAI. Aleksa Gordić discusses his work on multilingual AI, his path through Microsoft and DeepMind, and his decision to start OrtusAI. He describes YugoGPT, a language... - [Small Data, Big Impact: The Story Behind DuckDB](https://mlopstalks.com/talks/small-data-big-impact-the-story-behind-duckdb): Hannes Mühleisen, DuckDB Labs & Jordan Tigani, MotherDuck. Hannes Mühleisen explains that DuckDB started after researchers saw people struggle with large data systems while working with much smaller datasets. The project took an... - [Language, Graphs, and AI in Industry](https://mlopstalks.com/talks/language-graphs-and-ai-in-industry): Paco Nathan, Derwen, Inc.. Paco Nathan describes his work helping enterprise teams turn machine learning research and open-source software into production systems. He explains why smaller specialized models and... - [Founding, Funding, and the Future of MLOps](https://mlopstalks.com/talks/founding-funding-and-the-future-of-mlops): Mihail Eric, Storia AI. Mihail Eric talks with Demetrios Brinkmann about his path from Amazon Alexa and Stanford NLP to founding startups. His first attempt focused on data quality... - [Challenges Operationalizing ML (And Some Solutions)](https://mlopstalks.com/talks/challenges-operationalizing-ml-and-some-solutions): Nathan Ryan Frank, WW Grainger. Nathan Ryan Frank describes operationalizing machine learning through practical engineering habits and team design. He starts with tool selection: teams should understand the pain they... - [Inferring Creativity](https://mlopstalks.com/talks/inferring-creativity): Nick Hasty, GIPHY. Nick Hasty describes a career that moved from music and internet art to engineering, then to product and machine learning at GIPHY. He joined GIPHY... - [The Role of Infrastructure in ML Leveraging Open Source](https://mlopstalks.com/talks/the-role-of-infrastructure-in-ml-leveraging-open-source): Niels Bantilan, Union.ai. Niels Bantilan explains how Pandera grew from a personal solution to data-frame type errors into an open-source data validation project that later merged into Union.... - [LLMs in Focus: From One-Size Fits All to Verticalized Solutions](https://mlopstalks.com/talks/llms-in-focus-from-one-size-fits-all-to-verticalized-solutions): Venky Ganti & Laurel Orr, Numbers Station. Venky Ganti and Laurel Orr explain why general-purpose LLMs often struggle with enterprise data. A public model can write SQL for familiar schemas, but real... - [Model Management in a Regulated Environment](https://mlopstalks.com/talks/model-management-in-a-regulated-environment): Darek Kłeczek, Weights & Biases & Mark Huang, Gradient & Oliver Chipperfield, M-KOPA & Michelle Marie Conway, Lloyd's Banking Group. This round-table discussion explains model management as the work of tracking a model from its training data and evaluations through deployment, monitoring, replacement, and audit.... - [Building the Future of AI in Software Development](https://mlopstalks.com/talks/building-the-future-of-ai-in-software-development): Varun Mohan, Codeium. Varun Mohan describes how Exafunction became Codeium. Exafunction started with GPU virtualization for large deep learning workloads, eventually managing more than 10,000 GPUs for a... - [Scaling MLOps for Computer Vision](https://mlopstalks.com/talks/scaling-mlops-for-computer-vision): David Espejo, Union & Fabio Grätz, Recogni & Arno Hollosi, Blackshark.ai. The session presents three views of MLOps for computer vision. David Espejo introduces Flyte as a platform that connects model developers with operations through typed... - [DSPy: Transforming Language Model Calls into Smart Pipelines](https://mlopstalks.com/talks/dspy-transforming-language-model-calls-into-smart-pipelines): Omar Khattab, Stanford. Omar Khattab explains why DSPy treats language model applications as programs instead of collections of hand-tuned prompts. He traces the project from an earlier abstraction... - [LLMs in Biomaterials Production](https://mlopstalks.com/talks/llms-in-biomaterials-production): Pierre Salvy, Cambrium. Pierre Salvy describes Cambrium's work at the intersection of biotechnology, engineering, and AI. The company designs proteins that can be produced by genetically modified yeast... - [LLMs Mini Summit // MLOps Mini Summit Meetup #3](https://mlopstalks.com/talks/llms-mini-summit-mlops-mini-summit-meetup-3): Thomas Capelle, Weights & Biases & Boris Dayma, Craiyon & Jonathan Whitaker & Robbie McCorkell, Leap Labs. This meetup contains four short sessions about building and inspecting LLM systems. Thomas Capelle walks through a local voice assistant that calls tools. Prompt format... - [Enterprises Using MLOps, the Changing LLM Landscape, MLOps Pipelines](https://mlopstalks.com/talks/enterprises-using-mlops-the-changing-llm-landscape-mlops-pipelines): Chris Van Pelt, Weights & Biases. Chris Van Pelt describes how he and Lucas started CrowdFlower after using Amazon Mechanical Turk to collect labeled data for a search ranking model. After... - [Building Defensible AI Apps](https://mlopstalks.com/talks/building-defensible-ai-apps): Gregory Kamradt, DataIndependent. Gregory Kamradt and Demetrios Brinkmann discuss OpenAI DevDay, the GPT Store, GPT-4 Vision, retrieval, model lock-in, and product defensibility. Kamradt sees GPT-4 Vision through an... - [Model Blind Spot Discovery for Better Models](https://mlopstalks.com/talks/model-blind-spot-discovery-for-better-models): Pavol Bielik, LatticeFlow & David Garnitz, VectorFlow. This session combines two parts of the ML application pipeline. Pavol Bielik explains model blind spots, where a model looks strong on average but fails... - [Guarding LLM and NLP APIs: A Trailblazing Odyssey for Enhanced Security](https://mlopstalks.com/talks/guarding-llm-and-nlp-apis-a-trailblazing-odyssey-for-enhanced-security): Ads Dawson, Cohere. Ads Dawson explains how security work changes when an application includes an LLM. Traditional issues such as supply-chain attacks, rate limiting, and private-data access still... - [Designing for Forward Compatibility in Gen AI](https://mlopstalks.com/talks/designing-for-forward-compatibility-in-gen-ai): Rohit Agarwal, Portkey.ai. Rohit Agarwal describes the tooling needed to move generative AI applications from experiments into production. Drawing on large deployments, he discusses model error rates, spiky... - [Authoring Interactive, Shareable AI Evaluation Reports with Zeno](https://mlopstalks.com/talks/authoring-interactive-shareable-ai-evaluation-reports-with-zeno): Alex Cabrera, Carnegie Mellon University. Alex Cabrera argues that AI evaluation results lose much of their value when they are reduced to one score. A word error rate for an... - [Evaluating LLMs for AI Risk](https://mlopstalks.com/talks/evaluating-llms-for-ai-risk): Finn Howell, Robust Intelligence. Finn Howell presents red teaming as a way to find deficiencies in AI systems and produce recommendations for addressing them. She argues that teams should... - [The State of Open Source AI: Deployment Engines, Licences, & Hardware](https://mlopstalks.com/talks/the-state-of-open-source-ai-deployment-engines-licences-hardware): Casper da Costa-Luis, Premai. Casper da Costa-Luis discusses three parts of open source AI: licences, deployment software, and hardware. He explains why software licences do not answer what happens... - [AI Squared: Breaking LLMs out of the Chat Application](https://mlopstalks.com/talks/ai-squared-breaking-llms-out-of-the-chat-application): Benjamin Harvey, AI Squared. Benjamin Harvey argues that organizations need to move generative AI beyond standalone chat applications. Users often need an answer inside the tool they already use,... - [GenAI: An Unreliable Information Store](https://mlopstalks.com/talks/genai-an-unreliable-information-store): Noble Ackerson, Venta. Noble Ackerson argues that large language models are unreliable information stores because they are probabilistic, non-deterministic, and unaware of what they do not know. Their... - [Impact of LLMs on the Tech Stack and Product Development](https://mlopstalks.com/talks/impact-of-llms-on-the-tech-stack-and-product-development): Anand Das, Bito. Anand Das describes how Bito moved from an IDE collaboration product to an AI coding assistant. The change began with a simple Chrome extension that... - [Product Engineering for LLMs](https://mlopstalks.com/talks/product-engineering-for-llms): Charles Frye, Full Stack Deep Learning & Sahar Mor, Stripe & Sarah Guo, Conviction & Shyamala Prayaga, NVIDIA & Willem Pienaar. The panel discusses how teams can turn LLM capabilities into products that people can use and pay for. Sarah Guo points to legal workflows, code... - [Building RAG-based LLM Applications for Production](https://mlopstalks.com/talks/building-rag-based-llm-applications-for-production): Philipp Moritz & Yifei Feng, Anyscale. Philipp Moritz and Yifei Feng describe a question-answering assistant for Ray documentation, blogs, and books. They explain the RAG pipeline: load source documents, split them... - [Product Strategy for LLM Features When LLMs Aren't Your Product](https://mlopstalks.com/talks/product-strategy-for-llm-features-when-llms-arent-your-product): Harini Kannan. Harini Kannan argues that companies adding LLMs to existing products should keep ordinary product discipline. The customer problem remains the starting point, while the model... - [Assess the Value and Feasibility of LLM Use Cases with a Checklist](https://mlopstalks.com/talks/assess-the-value-and-feasibility-of-llm-use-cases-with-a-checklist): Rens Dimmendaal & Eva Bosma, Xebia Data. Rens Dimmendaal and Eva Bosma present a checklist for discussing LLM use cases with business and technical stakeholders. They start with an impact-feasibility matrix: teams... - [Building Effective Products with GenAI](https://mlopstalks.com/talks/building-effective-products-with-genai): Faizaan Charania, LinkedIn. Faizaan Charania explains how his technical background shapes his work as an AI product manager at LinkedIn. He starts with the user problem, checks what... - [Deploying LLMs on Structured Data Tasks: Lessons from the Trenches](https://mlopstalks.com/talks/deploying-llms-on-structured-data-tasks-lessons-from-the-trenches): Laurel Orr, Number Station. Laurel Orr explains why natural-language interfaces to enterprise data are easy to prototype and difficult to deploy. A general model can turn a business question... - [False Starts and Dead Ends: Building a Retrieval Augmented Generation System](https://mlopstalks.com/talks/false-starts-and-dead-ends-building-a-retrieval-augmented-generation-system): Wes Ladd, Train GRC. Wes Ladd describes the problems his team faced while building a retrieval augmented generation system for StinkBait, a cybersecurity research and reporting application from Train... - [Current State of LLMs in Production](https://mlopstalks.com/talks/current-state-of-llms-in-production): Apurva Misra, Truckstop. Apurva Misra explains how companies are putting LLM applications into production, with RAG as the most common starting point. She walks through the pipeline from... - [Data Quality's Impact on Large Language Models](https://mlopstalks.com/talks/data-qualitys-impact-on-large-language-models): Mona Rakibe & Maxim Lukichev, Telmai. Mona Rakibe and Maxim Lukichev argue that data quality directly affects the cost and usefulness of enterprise LLM projects. Companies are bringing years of data... - [From Building Self-driving Cars to Building LLM Applications](https://mlopstalks.com/talks/from-building-self-driving-cars-to-building-llm-applications): Effy Zhang, Baserun. Effy Zhang applies lessons from Cruise's self-driving car systems to LLM applications. She explains that both systems produce complex outputs that need more analysis than... - [The Future of Feature Stores and Platforms](https://mlopstalks.com/talks/the-future-of-feature-stores-and-platforms): Mike Del Balso, Tecton & Josh Wills, Angel Investor. Mike Del Balso traces feature platforms back to the production ML systems he saw at Google and helped build at Uber's Michelangelo. Large-scale models depended... - [Efficient Serving of LLMs for Experimentation and Production with Fireworks.ai](https://mlopstalks.com/talks/efficient-serving-of-llms-for-experimentation-and-production-with-fireworks-ai): Dmytro Dzhulgakov, Fireworks.ai. Dmytro Dzhulgakov describes how teams move from experimenting with many LLM variants to serving them in production. He explains why fine-tuning is useful for business... - [Lessons on Data Teams Leadership](https://mlopstalks.com/talks/lessons-on-data-teams-leadership): Luigi Patruno, 2U, Inc. Luigi Patruno describes how his work changed after moving from individual contributor to data science leader. He starts with the business problem, defines a measurable... - [LLM Valley](https://mlopstalks.com/talks/llm-valley): Lilly Chen, Contenda. Lilly Chen uses a video-game theme to explain how venture investors evaluate generative AI companies. She divides the market into B2B SaaS, B2C products, open... - [LLMs in Production at GetYourGuide](https://mlopstalks.com/talks/llms-in-production-at-getyourguide): Meghana Satish & Tina Treimane, GetYourGuide. Tina Treimane and Meghana Satish describe how GetYourGuide decides where LLMs fit and how it puts them into production. Tina frames the opportunity around conversational... - [Amplifying Impact with Generative AI: Insights from 10,000 Colleagues](https://mlopstalks.com/talks/amplifying-impact-with-generative-ai-insights-from-10-000-colleagues): Paul van der Boor, Prosus. Paul van der Boor describes how Prosus explored generative AI across a group of technology companies serving about two billion users. Its Plus One tool... - [Exploring the Latency/Throughput & Cost Space for LLM Inference](https://mlopstalks.com/talks/exploring-the-latency-throughput-cost-space-for-llm-inference): Timothée Lacroix, Mistral. Timothée Lacroix explains how to reason about serving an open-source language model by looking at throughput, per-token latency, and cost together. During decoding, each step... - [The Truth About AI Agents](https://mlopstalks.com/talks/the-truth-about-ai-agents): Silen Naihin, AutoGPT. Silen Naihin explains how current language-model agents differ from older reinforcement-learning agents. A language model acts as the agent's processing engine, producing plans and actions,... - [Translating Business Goals into Product Decisions](https://mlopstalks.com/talks/translating-business-goals-into-product-decisions): Richa Sachdev, JP Morgan Chase. Richa Sachdev describes how her career moved from software engineering into data engineering, machine learning, reporting, and process automation. At Vanguard, she helped establish data... - [Observability for LLMs](https://mlopstalks.com/talks/observability-for-llms): Phillip Carter, Honeycomb. Phillip Carter argues that observability has to be part of the engineering toolkit for reliable LLM features. A team can ship an initial product quickly,... - [Unlocking Real-World LLM Use Cases](https://mlopstalks.com/talks/unlocking-real-world-llm-use-cases): Hamsa Buvaraghan, Google Cloud. Hamsa Buvaraghan explains how teams can move from broad enthusiasm about generative AI to practical enterprise use cases. She covers applications such as document summarization,... - [AI in Education Fireside Chat](https://mlopstalks.com/talks/ai-in-education-fireside-chat): Klinton Bicknell, Duolingo & Bill Salak, Brainly & Yeva Hyusyan, SoloLearn. This fireside chat examines how Duolingo, Brainly, and SoloLearn are using AI in learning products. Yeva Hyusyan describes work on models that produce content in... - [Automating Data Annotation with LLMs](https://mlopstalks.com/talks/automating-data-annotation-with-llms): Nikolai Liubimov, Michael Malyuk & Chris Hoge, HumanSignal. The workshop presents a human-in-the-loop workflow for using LLMs to label data. Chris Hoge explains why human annotations remain the reference point while large models... - [MLOps vs ML Orchestration](https://mlopstalks.com/talks/mlops-vs-ml-orchestration): Ketan Umare, Union.ai. Ketan Umare and Stephen Batifol discuss where ML orchestration differs from ordinary data workflow orchestration, using Flyte and Union as the main examples. Ketan explains... - [Finetuning Open-Source LLMs](https://mlopstalks.com/talks/finetuning-open-source-llms): Sebastian Raschka, Lightning AI. Sebastian Raschka explains how pretrained language models can be used before discussing fine-tuning. Prompting changes the model's input, while retrieval-augmented generation adds information from a... - [Fireside Chat with LLM Startups](https://mlopstalks.com/talks/fireside-chat-with-llm-startups): Paul van der Boor & Sandeep Bakshi, ProsusGroup & Shriyash Upadhyay, Martian & Lars Maaløe, Corti & Pietro Gagliano, Transitional Forms. This panel brings together founders building companies around different uses of generative AI. Pietro Gagliano describes Transitional Forms as an entertainment innovation company that connects... - [What Drives GenAI Development in the Next 3 Years](https://mlopstalks.com/talks/what-drives-genai-development-in-the-next-3-years): Euro Beinat, Prosus. Euro Beinat describes the forces he expects to shape Generative AI over the next few years. He starts with scaling laws: more compute, data, and... - [MLOps at GetYourGuide](https://mlopstalks.com/talks/mlops-at-getyourguide): Jean Machado, Meghana Satish, Olivia Houghton & Theodore Meynard, GetYourGuide. GetYourGuide's ML platform grew from an engineering standards initiative during the COVID downturn, when the company had time to invest in infrastructure for its future... - [The Centralization of Power in AI](https://mlopstalks.com/talks/the-centralization-of-power-in-ai): Kyle Harrison, Contrary. Kyle Harrison discusses how the ChatGPT moment made existing progress in transformer-based models visible to the wider market. He divides AI companies into incumbents with... - [Adventures in Building CLIP & Other (Largeish) LMs](https://mlopstalks.com/talks/adventures-in-building-clip-other-largeish-lms): Sachin Abeywardana, Canva AI. Sachin Abeywardana discusses his move from Bayesian machine learning research into deep learning and industry work at Canva. He explains why he values deep learning... - [All About Evaluating LLM Applications](https://mlopstalks.com/talks/all-about-evaluating-llm-applications): Shahul Es, Exploding Gradients. Shahul Es explains evaluation as measuring and quantifying a system before iterating on it. He is skeptical of public LLM leaderboards because models can be... - [LLM Security](https://mlopstalks.com/talks/llm-security): Raahul Dutta, Elsevier & Uri Shamay, Null & Sankalp Gilda, DevelopYours. This Mini Summit combines three talks. Sankalp Gilda introduces tsbootstrap, a Python library for resampling time-series data with methods such as moving, stationary, circular, and... - [Building an ML Platform: Insights, Community, and Advocacy](https://mlopstalks.com/talks/building-an-ml-platform-insights-community-and-advocacy): Stephen Batifol, Wolt. Stephen Batifol describes how Wolt built an internal ML platform and how his role moved from platform engineering into internal developer advocacy. The platform runs... - [Introduction to QA bots with RAGs and LLMs](https://mlopstalks.com/talks/introduction-to-qa-bots-with-rags-and-llms): . Rahul introduces a course on building question-and-answer systems over proprietary data with large language models and retrieval augmented generation. He explains that LLMs are powerful... - [Tecton Round-table // Get your ML Application Into Production](https://mlopstalks.com/talks/tecton-round-table-get-your-ml-application-into-production): Kevin Stumpf, Derek Salama, Eddie Esquivel & Isaac Cameron, Tecton. The roundtable examines why traditional ML applications remain difficult to put into production. Eddie Esquivel describes friction between data scientists and the teams that must... - [Collaboration and Strategy](https://mlopstalks.com/talks/collaboration-and-strategy): Vin Vashishta, V Squared. Vin Vashishta argues that data and AI work only creates business value when teams understand the strategy behind a project. Generative AI has sped up... - [From Virtualization to AI Integration](https://mlopstalks.com/talks/from-virtualization-to-ai-integration): Lamia Youseff, JazzComputing. Lamia Youseff describes a career that moved from early AI research into high-performance computing, virtualization, cloud infrastructure, and product work at Google, Microsoft, Apple, and... - [Harnessing MLOps in Finance](https://mlopstalks.com/talks/harnessing-mlops-in-finance): Michelle Marie Conway, Lloyds Banking Group. Michelle Marie Conway describes her move from mathematical statistics into data science and machine learning engineering at Lloyds Banking Group. She explains why Python fundamentals,... - [Building Cody, an Open Source AI Coding Assistant](https://mlopstalks.com/talks/building-cody-an-open-source-ai-coding-assistant): Beyang Liu, Sourcegraph. Beyang Liu explains why Sourcegraph started with code search and how that work led to Cody, its AI coding assistant. Developers spend much of their... - [FrugalGPT: Better Quality and Lower Cost for LLM Applications](https://mlopstalks.com/talks/frugalgpt-better-quality-and-lower-cost-for-llm-applications): Lingjiao Chen, Stanford University. Lingjiao Chen explains how FrugalGPT reduces the cost of applications that call large language models. He frames hosted LLMs as providers in a marketplace, with... - [Building RedPajama](https://mlopstalks.com/talks/building-redpajama): Vipul Ved Prakash, Together. Vipul Ved Prakash explains why building capable language models requires more than publishing model weights. Data volume, compute, model size, and infrastructure all scale together,... - [LLM-based Feature Extraction for Operational Optimization](https://mlopstalks.com/talks/llm-based-feature-extraction-for-operational-optimization): Xin Lian, Canva. Xin Lian describes two Canva use cases for LLM-based feature extraction. The first categorizes user search queries into branches of Canva's content architecture. A traditional... - [LLMs vs LMs in Production](https://mlopstalks.com/talks/llms-vs-lms-in-production): Denys Linkov, Voiceflow. Denys Linkov compares Voiceflow's use of large language models with its smaller, task-specific language models. Voiceflow added large language models for assistant creation, runtime generation,... - [Fireside Chat - The Future of LLMs](https://mlopstalks.com/talks/fireside-chat-the-future-of-llms): David Hershey, Unusual Ventures & Daniel Jeffries, AI Infrastructure Alliance. David Hershey and Daniel Jeffries discuss where language models are useful today and where expectations have run ahead of reality. They argue for focused applications... - [MLOps LLM Stack Hackathon Winner](https://mlopstalks.com/talks/mlops-llm-stack-hackathon-winner): Travis Cline, Virta Health. Travis Cline describes the project that won the MLOps Community hackathon, a 12-hour, in-person event. The team used 10,000 embeddings from MLOps Community Slack conversations... - [Preemption Chaos and Optimizing Server Startup](https://mlopstalks.com/talks/preemption-chaos-and-optimizing-server-startup): Bradley Heilbrun, Replit. Bradley Heilbrun explains how Replit used preemptible GPU nodes for LLM serving even though Google warns against using them for highly available services. An A100... - [Taming AI Product Development Through Test-driven Prompt Engineering](https://mlopstalks.com/talks/taming-ai-product-development-through-test-driven-prompt-engineering): Maxime Beauchemin, Preset. Maxime Beauchemin argues that teams building AI features should treat prompts more like product code than casual chat instructions. LLMs differ from ordinary APIs because... - [Considerations and Optimizations for Deploying Open Source LLMs at Your Company](https://mlopstalks.com/talks/considerations-and-optimizations-for-deploying-open-source-llms-at-your-company): Oscar Rovira, Mystic AI. Oscar Rovira describes the engineering work required to turn an open source LLM into a fast, secure, scalable API. Each model may need different libraries... - [Enabling Defense Missions with Local LLMs](https://mlopstalks.com/talks/enabling-defense-missions-with-local-llms): Gerred Dillon, Defense Unicorns. Gerred Dillon explains why defense and other regulated environments need local language models. These environments may be air-gapped, placed at the edge, tightly controlled for... - [LLM XGBoost: Can a Fine-Tuned LLM Beat XGBoost on Tabular Data?](https://mlopstalks.com/talks/llm-xgboost-can-a-fine-tuned-llm-beat-xgboost-on-tabular-data): Sebastian Cattes, iwt. Sebastian Cattes tested whether a fine-tuned large language model could classify tabular data as well as XGBoost. He chose a recently published telecommunications customer-churn dataset... - [Using LLMs to Power Consumer Search at Scale](https://mlopstalks.com/talks/using-llms-to-power-consumer-search-at-scale): Aravind Srinivas, Perplexity AI. Aravind Srinivas introduces Perplexity as a conversational search engine built to answer questions with citations and current web information. He explains how Copilot asks clarifying... - [Using Large Language Models at AngelList](https://mlopstalks.com/talks/using-large-language-models-at-angellist): Thibaut Labarre, AngelList. Thibaut Labarre explains how AngelList moved from conventional machine learning to large language models for text-heavy investing workflows. His first system classified news articles so... - [Evolving AI Governance for an LLM World](https://mlopstalks.com/talks/evolving-ai-governance-for-an-llm-world): Diego Oppenheimer, Factory. Diego Oppenheimer explains why governance frameworks built around individual machine learning models do not map cleanly to LLM applications. Traditional governance tracks model provenance, training... - [LIMA: Less is More for Alignment](https://mlopstalks.com/talks/lima-less-is-more-for-alignment): Chunting Zhou, FAIR Labs. Chunting Zhou presents LIMA, a LLaMA-based chatbot fine-tuned on 1,000 curated examples. The examples combine public sources such as Stack Exchange, WikiHow, writing prompts, and... - [MLOps vs LLMOps](https://mlopstalks.com/talks/mlops-vs-llmops): Richa Sachdev, JPMorgan Chase & Willem Pienaar, Feast & Chris Van Pelt, Weights & Biases & Aparna Dhinakaran, Arize AI & Alex Ratner, Snorkel. The panel compares the operating practices around traditional machine learning with those emerging around large language models. Willem Pienaar says LLM applications can begin with... - [All the Hard Stuff with LLMs in Product Development](https://mlopstalks.com/talks/all-the-hard-stuff-with-llms-in-product-development): Phillip Carter, Honeycomb. Phillip Carter describes how Honeycomb built and shipped a natural-language query assistant for its observability product. The assistant turns user requests into a JSON query... - [End-to-end Modern Machine Learning in Production](https://mlopstalks.com/talks/end-to-end-modern-machine-learning-in-production): Omar Sanseviero, Hugging Face. Omar Sanseviero gives a short tour of tools and techniques for putting large language models into products. He first covers inference, using examples such as... - [Everything We've Been Taught About ML is Wrong](https://mlopstalks.com/talks/everything-weve-been-taught-about-ml-is-wrong): Emmanuel Ameisen, Anthropic. Emmanuel Ameisen revisits the ML rules he used to teach, including starting with a simple model, using task-specific data, avoiding model-generated data, and keeping models... - [Guardrails for LLMs: A Practical Approach](https://mlopstalks.com/talks/guardrails-for-llms-a-practical-approach): Shreya Rajpal, Guardrails AI. Shreya Rajpal explains why prompts alone are a weak way to control LLM applications. Models are stochastic, so the same input can produce different outputs,... - [UX of an LLM User](https://mlopstalks.com/talks/ux-of-an-llm-user): Misty Free, Jasper & Davis Treybig, Innovation Endeavors & Dina Yerlan, Adobe Firefly & Artem Harutyunyan, Bardeen AI. This panel examines how people should interact with products built on large language models. Artem Harutyunyan describes Bardeen's approach of showing users a generated automation... - [Bringing Structure to Unstructured Data with an AI-First System Design](https://mlopstalks.com/talks/bringing-structure-to-unstructured-data-with-an-ai-first-system-design): Will Gaviria Rojas, Coactive AI. Will Gaviria Rojas argues that AI systems need data designs built around unstructured content rather than storage formats created for traditional data. A JSON key-value... - [Incorporating LLMs in High-stake Use Cases](https://mlopstalks.com/talks/incorporating-llms-in-high-stake-use-cases): Yada Pruksachatkun, Moonhub. Yada Pruksachatkun explains why LLM applications in medicine, law, therapy, and other high-stakes settings need more than strong headline results. She uses a therapy bot... - [RLHF Data Collection in Practice](https://mlopstalks.com/talks/rlhf-data-collection-in-practice): Andrew Mauboussin, Surge AI. Andrew Mauboussin explains how Surge AI collects data for the two main stages of RLHF. Supervised fine-tuning uses thousands to tens of thousands of prompt-completion... - [The Confidence Checklist for LLMs in Production](https://mlopstalks.com/talks/the-confidence-checklist-for-llms-in-production): Rohit Agarwal, portkey.ai. Rohit Agarwal presents six production practices based on his experience with large LLM deployments: validate outputs, prepare for abusive traffic, control user limits, reduce perceived... - [MLOps at the Age of Generative AI](https://mlopstalks.com/talks/mlops-at-the-age-of-generative-ai): Barak Turovsky, Scale Venture Partners. Barak Turovsky compares the current spread of large language models with the earlier AI wave that brought deep neural networks and custom hardware into Google... - [Building Recommender Systems with Large Language Models](https://mlopstalks.com/talks/building-recommender-systems-with-large-language-models): Sumit Kumar, Meta. Sumit Kumar explains how large language models are being used in recommendation systems and why researchers are interested in them. LLMs can add web-scale knowledge... - [Combining LLMs with Knowledge Bases to Prevent Hallucinations](https://mlopstalks.com/talks/combining-llms-with-knowledge-bases-to-prevent-hallucinations): Scott Mackie, Mem. Scott Mackie explains how to build an assistant that answers from a controlled knowledge base instead of relying only on an LLM's training data. He... - [Designing Human in the Loop Experiences for LLMs](https://mlopstalks.com/talks/designing-human-in-the-loop-experiences-for-llms): Alberto Rizzoli, V7. Alberto Rizzoli argues that production teams have made limited progress on human-in-the-loop experiences for LLMs. The work includes more than labeling. People also need ways... - [Unleashing Code Completion with LLMs](https://mlopstalks.com/talks/unleashing-code-completion-with-llms): Monmayuri Ray, GitLab. Monmayuri Ray describes GitLab's early work building code completion tools and the decisions involved in taking LLMs into production. She evaluates suggestions against three practical... - [Experiment Tracking in the Age of LLMs](https://mlopstalks.com/talks/experiment-tracking-in-the-age-of-llms): Piotr Niedźwiedź, Neptune. Piotr Niedźwiedź explains how his path from software engineering and competitive programming led to Codilime, DeepSense.ai, and Neptune. Neptune began as an internal experiment tracker... - [Controlled and Compliant AI Applications](https://mlopstalks.com/talks/controlled-and-compliant-ai-applications): Daniel Whitenack, Prediction Guard. Daniel Whitenack describes the practical problems that appear when large language models move from chat demos into production systems. Their output is often inconsistent, unstructured... - [Making LLM Inference Affordable](https://mlopstalks.com/talks/making-llm-inference-affordable): Daniel Campos, Snowflake. Daniel Campos argues that many businesses do not need a large foundational model to perform every task. A smaller model trained for a narrow job... - [The Next Million AI Apps](https://mlopstalks.com/talks/the-next-million-ai-apps): Mark Huang, Preemo. Mark Huang presents a practical workshop on adapting open language models for specialized applications. He compares closed models, open models, and smaller task-specific models, then... - [Challenges in Providing LLMs as a Service](https://mlopstalks.com/talks/challenges-in-providing-llms-as-a-service): Hemant Jain, Cohere AI. Hemant Jain describes the engineering problems Cohere has faced while productionizing language models as services. Large models can exceed the capacity of one accelerator, so... - [Lessons Learned Productionising LLMs for Stripe Support](https://mlopstalks.com/talks/lessons-learned-productionising-llms-for-stripe-support): Sophie Daly, Stripe. Sophie Daly describes Stripe's first LLM application for support agents. The system did not answer customers directly. It prompted agents with responses that were meant... - [LLM on Kubernetes](https://mlopstalks.com/talks/llm-on-kubernetes): Shrinand Javadekar, Outerbounds & Manjot Pahwa, Lightspeed India & Rahul Parundekar, A.I. Hero & Patrick Barker. The panel discusses where Kubernetes fits in LLM work, from foundation-model training and fine-tuning to inference and applications that combine models with vector databases and... - [Transforming AI Safety & Security](https://mlopstalks.com/talks/transforming-ai-safety-security): Manojkumar Parmar, AIShield, a Corporate Startup of Bosch. Manojkumar Parmar presents AIShield.GuArdIan as a control layer for enterprise use of generative AI. He describes the problem as a choice between adopting LLMs without... - [Building Products](https://mlopstalks.com/talks/building-products): Sam Charrington, TWIML AI Podcast & George Mathew, Insight Partners & Asmitha Rathis, PromptOps & Natalia Burina, Meta & Sahar Mor, Stripe. This panel examines the practical decisions involved in building products with large language models. Natalia Burina frames model fit around fluency and accuracy. Creative writing... - [Linguistically-informed LLMs Perform Better](https://mlopstalks.com/talks/linguistically-informed-llms-perform-better): Chris Brousseau, Mastercard. Chris Brousseau argues that large language models should be designed with language itself in mind. He uses syntax, morphology, semantics, pragmatics, and phonetics to explain... - [LLMs For the Rest of Us](https://mlopstalks.com/talks/llms-for-the-rest-of-us): Vikram Sreekanti, Aqueduct & Joseph Gonzalez, UC Berkeley and Aqueduct. Joseph Gonzalez describes two perspectives on LLMs: Berkeley's work on model and systems research, and Aqueduct's focus on what software teams need today. He explains... - [Navigating Through the Generative AI Landscape](https://mlopstalks.com/talks/navigating-through-the-generative-ai-landscape): Azin Asgarian, Georgian. Azin Asgarian gives startups a way to think about the rapidly changing generative AI field. She compares models by size, architecture, training data, objectives, task... - [Building Reliable AI Agents](https://mlopstalks.com/talks/building-reliable-ai-agents): Travis Fischer. Travis Fischer argues that most AI agents in 2023 are still toys, despite the attention around AutoGPT and similar projects. He defines an agent as... - [Create a Contextual Chatbot with LLM and a Vector Database in 10 Minutes](https://mlopstalks.com/talks/create-a-contextual-chatbot-with-llm-and-a-vector-database-in-10-minutes): Raahul Dutta, Elsevier. Raahul Dutta describes a chatbot built at Elsevier to reduce the manual work involved in reviewing research about topics such as lithium policy. The system... - [Foundation Models in the Modern Data Stack](https://mlopstalks.com/talks/foundation-models-in-the-modern-data-stack): Ines Chami, Numbers Station. Ines Chami explains how foundation models can handle structured data tasks in the modern data stack. She covers natural-language SQL generation, cleaning records with prompts,... - [Wardley Mapping Prompt Engineering](https://mlopstalks.com/talks/wardley-mapping-prompt-engineering): Mark Craddock. Mark Craddock introduces Wardley Mapping as a way to plan strategy around user needs, value chains, dependencies, and the movement of technology from Genesis through... - [Treating Prompt Engineering More Like Code](https://mlopstalks.com/talks/treating-prompt-engineering-more-like-code): Maxime Beauchemin, Preset. Maxime Beauchemin explains why language model APIs need a testing discipline closer to software engineering. Traditional APIs have documented schemas and mostly deterministic outputs. Prompts... - [Eliminating Garbage In/Garbage Out for Analytics and ML](https://mlopstalks.com/talks/eliminating-garbage-in-garbage-out-for-analytics-and-ml): Roy Hasson & Santona Tuli, Upsolver. Roy Hasson and Santona Tuli discuss why data and ML teams need to think like product teams. Roy describes the limits of reactive data tests:... - [Evaluating LLM-based Applications](https://mlopstalks.com/talks/evaluating-llm-based-applications): Josh Tobin, Gantry. Josh Tobin explains why evaluating LLM applications differs from evaluating traditional machine learning systems. With an off-the-shelf language model, the original training distribution is usually... - [Evaluation](https://mlopstalks.com/talks/evaluation-panel-1-large-language-models-in-production-conference-part-2): Abi Aryan, Independent Consultant & Amrutha Gujjar, Structured & Josh Tobin, Gantry & Sohini Roy, NVIDIA. The panel explains why evaluating large language model applications differs from evaluating traditional machine learning systems. Josh Tobin says teams often begin with a desired... - [It Worked When I Prompted It](https://mlopstalks.com/talks/it-worked-when-i-prompted-it): Soham Chatterjee, Sleek. Soham Chatterjee describes six months of building Speaker Scribe and the problems that appeared when an LLM product moved beyond a proof of concept. External... - [Solving LLM Data Problems](https://mlopstalks.com/talks/solving-llm-data-problems): Yujian Tang, Zilliz. Yujian Tang explains why LLM applications need more than a language model. Models can lack domain knowledge, contain outdated information, hallucinate plausible code, and become... - [Python Power: How Daft Embeds Models and Revolutionizes Data Processing](https://mlopstalks.com/talks/python-power-how-daft-embeds-models-and-revolutionizes-data-processing): Sammy Sidhu, Eventual. Sammy Sidhu describes a career that moved from high-performance computing at Berkeley to autonomous vehicle systems at DeepScale, Tesla, Lyft Level 5, and Toyota. He... - [Building and Curating Datasets for RLHF and LLM Fine-tuning](https://mlopstalks.com/talks/building-and-curating-datasets-for-rlhf-and-llm-fine-tuning): Daniel Vila Suero, Argilla. Daniel Vila Suero explains how to collect and manage data for supervised fine-tuning and reinforcement learning from human feedback. He defines feedback broadly. It can... - [Stopping Hallucinations From Hurting Your LLMs](https://mlopstalks.com/talks/stopping-hallucinations-from-hurting-your-llms): Atindriyo Sanyal, Galileo. Atindriyo Sanyal explains hallucinations as a data quality problem in LLM systems. They include factual errors and misleading answers that sound plausible. He traces them... - [Understanding the LLM Economics](https://mlopstalks.com/talks/understanding-the-llm-economics): Nikunj Bajaj, TrueFoundry. Nikunj Bajaj explains how to estimate the cost of LLM applications through a worked example: summarizing six million Wikipedia articles from about 1,000 tokens each... - [Beyond the Hype: Monitoring LLMs in Production](https://mlopstalks.com/talks/beyond-the-hype-monitoring-llms-in-production): Claire Longo, Arize. Claire Longo explains how monitoring an LLM system differs from monitoring a conventional tabular machine learning model. An LLM application may include a user query,... - [Build and Customize LLMs in Less than 10 Lines of YAML](https://mlopstalks.com/talks/build-and-customize-llms-in-less-than-10-lines-of-yaml): Travis Addair, Predibase. Travis Addair explains how teams can adapt existing large language models to specific business tasks without taking on the cost of pretraining. He describes a... - [Building Production Copilots](https://mlopstalks.com/talks/building-production-copilots): Tristan Zajonc, Continual. Tristan Zajonc argues that AI copilots will become features inside existing SaaS applications rather than replacing those applications or being controlled by one universal assistant.... - [Embeddings and Retrieval for LLMs: Techniques and Challenges](https://mlopstalks.com/talks/embeddings-and-retrieval-for-llms-techniques-and-challenges): Anton Troynikov, Chroma. Anton Troynikov explains how embeddings let an application add external context to an LLM. Data is mapped into vectors, queries are embedded in the same... - [Open Source and Fast Decision Making](https://mlopstalks.com/talks/open-source-and-fast-decision-making): Rob Hirschfeld, RackN. Rob Hirschfeld and Demetrios Brinkmann discuss what has changed in infrastructure since Hirschfeld and Dave McCrory worked on early cloud systems. Hirschfeld says the industry... - [Pitfalls and Best Practices: 5 Lessons from LLMs in Production](https://mlopstalks.com/talks/pitfalls-and-best-practices-5-lessons-from-llms-in-production): Raza Habib, Humanloop. Raza Habib shares lessons from Humanloop's work with companies building large language model applications. He describes an LLM application as traditional software around a base... - [Scalable Evaluation and Serving of Open Source LLMs](https://mlopstalks.com/talks/scalable-evaluation-and-serving-of-open-source-llms): Waleed Kadous, Anyscale. Waleed Kadous shares the first production lessons from building and running Aviary, Anyscale's open source LLM serving and evaluation system. He compares commercial APIs, hosted... - [Taking ImgFlip's 'This Meme Does Not Exist' to the Next Level with a LLM](https://mlopstalks.com/talks/taking-imgflips-this-meme-does-not-exist-to-the-next-level-with-a-llm): Stefan Ojanen, Genesis Cloud. Stefan Ojanen describes a Genesis Cloud project that uses a large language model to generate captions for ImgFlip meme templates. The team worked with 650,000... - [Using Vector Databases: Practical Advice for Production](https://mlopstalks.com/talks/using-vector-databases-practical-advice-for-production): Sam Partee, Redis. Sam Partee explains how vector embeddings turn unstructured data into searchable numerical representations, then focuses on the production patterns he has deployed with customers and... - [Building LLM Applications for Production](https://mlopstalks.com/talks/building-llm-applications-for-production): Chip Huyen, Claypot AI. Chip Huyen discusses the production problems that remain after an LLM can generate a convincing response. Small input changes can cause large output changes, and... - [Large Model Training and Inference with DeepSpeed](https://mlopstalks.com/talks/large-model-training-and-inference-with-deepspeed): Samyam Rajbhandari, Microsoft DeepSpeed. Samyam Rajbhandari explains how DeepSpeed developed from an early fix for slow distributed training into a collection of systems for large-model training and inference. The... - [LLMs as Intelligent Assistants](https://mlopstalks.com/talks/llms-as-intelligent-assistants): Sarah Aerni, Salesforce. Sarah Aerni presents LLMs as assistants embedded in Salesforce workflows rather than as fully autonomous replacements for employees. She walks through examples for sales, service,... - [The Emerging Toolkit for Reliable, High-quality LLM Applications](https://mlopstalks.com/talks/the-emerging-toolkit-for-reliable-high-quality-llm-applications): Matei Zaharia, Databricks. Matei Zaharia describes the practical problems that appear when fluent language models are put into production. They can give incorrect facts, generate unsuitable code, change... - [Democratizing AI](https://mlopstalks.com/talks/democratizing-ai): Yujian Tang, Zilliz. Yujian Tang explains why vector databases became widely discussed after ChatGPT. LLMs have fixed training cutoffs, while companies need to use current, private, and domain-specific... - [From Arduinos to LLMs: Exploring the Spectrum of ML](https://mlopstalks.com/talks/from-arduinos-to-llms-exploring-the-spectrum-of-ml): Soham Chatterjee, Sleek. Soham Chatterjee describes a career that began in electrical engineering and moved through IoT, deep learning, edge computing, and TinyML. He explains how an Arduino... - [Dataframes Are All You Need: MLOps on Easy Mode](https://mlopstalks.com/talks/dataframes-are-all-you-need-mlops-on-easy-mode): Jay Chia, Eventual. Jay Chia argues that teams can start an MLOps stack with a good data frame library on top of storage, rather than assembling many separate... - [LLMs in Production Conference - Part II](https://mlopstalks.com/talks/llms-in-production-conference-part-ii): Matei Zaharia, Databricks and Stanford & Chip Huyen. Demetrios Brinkmann opens with findings from the LLMs in Production survey. He describes an emerging stack around foundation models, vector databases, developer SDKs, model tuning,... - [The Long Tail of ML Deployment](https://mlopstalks.com/talks/the-long-tail-of-ml-deployment): Tuhin Srivastava, Baseten. Tuhin Srivastava describes his move from investment banking to machine learning research and then to building production systems. He says that training a model in... - [Clean Code for Data Scientists](https://mlopstalks.com/talks/clean-code-for-data-scientists): Matt Sharp, Shopify. Matt Sharp argues that data scientists should treat programming as part of their craft, even when their main work involves statistics, analysis, or research. He... - [Fine-Tuning LLMs: Best Practices and When to Go Small](https://mlopstalks.com/talks/fine-tuning-llms-best-practices-and-when-to-go-small): Mark Kim-Huang, Preemo Inc.. Mark Kim-Huang compares closed-source models, fine-tuned open-source models, and small specialized models. He explains why teams may need custom models when they require control over... - [Why is MLOps Hard in an Enterprise?](https://mlopstalks.com/talks/why-is-mlops-hard-in-an-enterprise): Maria Vechtomova & Basak Eskili, Ahold Delhaize. Maria Vechtomova and Basak Eskili describe how Ahold Delhaize standardizes machine learning across 19 brands. The brands have different levels of data science capability, yet... - [Guiding LLMs While Staying in the Driver's Seat](https://mlopstalks.com/talks/guiding-llms-while-staying-in-the-drivers-seat): Jacob van Gogh, Adept AI. Jacob van Gogh describes Adept AI's natural-language software collaborator, which controls a mouse and keyboard to carry out tasks in tools such as Airbnb and... - [Using LLMs to Punch Above Your Weight!](https://mlopstalks.com/talks/using-llms-to-punch-above-your-weight): Cameron Feenstra, Anzen. Cameron Feenstra explains how Anzen, a small insurance company, uses language models to move quickly against larger incumbents. The first example is insurance underwriting. An... - [Reasoning Machines](https://mlopstalks.com/talks/reasoning-machines): Justin Uberti, Fixie.ai & Jon Turow, Madrona Venture Group. Justin Uberti and Jon Turow argue that large language models should be treated as reasoning machines rather than fact machines. Models can generalize, summarize, and... - [No Rose Without a Thorn - Obstacles to Successful LLM Deployments](https://mlopstalks.com/talks/no-rose-without-a-thorn-obstacles-to-successful-llm-deployments): Tanmay Chopra, Neeva. Tanmay Chopra argues that LLM demos often avoid the conditions that make production difficult. The main infrastructure problems are slow responses, the buy-versus-build decision, rising... - [Efficiently Scaling and Deploying LLMs](https://mlopstalks.com/talks/efficiently-scaling-and-deploying-llms): Hanlin Tang, MosaicML. Hanlin Tang argues that the future of large language models will include many small, specialized models owned by individual companies. Companies may still use external... - [Cohere Large Language Model at Scale](https://mlopstalks.com/talks/cohere-large-language-model-at-scale): Nils Reimers, Cohere. Nils Reimers explains how his move from IT security and academic research led him toward building machine learning systems for users. He discusses security risks... - [Data Privacy and Security](https://mlopstalks.com/talks/data-privacy-and-security): Diego Oppenheimer, Factory & Gevorg Karapetyan, ZERO Systems & Vin Vashishta, V Squared & Saahil Jain, U.com & Shreya Rajpal. This panel discusses privacy, security, trust, and practical adoption of large language models. Vin Vashishta argues that models can uncover complex patterns in public data,... - [Agentic Relationship Management](https://mlopstalks.com/talks/agentic-relationship-management): Ashe Magalhaes, Hearth AI. Ashe Magalhaes introduces Hearth AI's idea of agentic relationship management. The product is intended to help people handle complex personal and professional networks by enriching... - [Building Defensible Products with LLMs](https://mlopstalks.com/talks/building-defensible-products-with-llms): Raza Habib, Humanloop. Raza Habib explains how Humanloop sees teams build LLM applications from prototypes into production. He breaks an application into a base model, a prompt template,... - [MLOps Build or Buy, Startup vs. Enterprise?](https://mlopstalks.com/talks/mlops-build-or-buy-startup-vs-enterprise): Aaron Maurer & Katrina Ni, Slack. Aaron Maurer and Katrina Ni describe how Slack built a shared recommendation platform for many product teams. The platform exposes a simple API for requesting... - [Cost Optimization and Performance](https://mlopstalks.com/talks/cost-optimization-and-performance): Lina Weichbrodt & Luis Ceze, OctoML & Jared Zoneraich, Prompt Layer & Daniel Campos, Neeva & Mario Kostelac, Intercom. The panel discusses the cost and performance decisions involved in putting large language models into production. Daniel Campos describes Neeva's move from foundation-model APIs to... - [What is the role of ML Engineers in the time of GPT4 and BARD?](https://mlopstalks.com/talks/what-is-the-role-of-ml-engineers-in-the-time-of-gpt4-and-bard): Hannes Hapke, Digits. Hannes Hapke compares the arrival of large language model APIs with the printing press. APIs make machine learning available to domain experts, but they also... - [Generative Interfaces Beyond Chat](https://mlopstalks.com/talks/generative-interfaces-beyond-chat): Linus Lee, Notion. Linus Lee argues that chat is a useful starting point for working with language models, but it should not be the only interface. Chat makes... - [Machine Learning Education at Uber](https://mlopstalks.com/talks/machine-learning-education-at-uber): Melissa Barr & Michael Mui, Uber. Melissa Barr and Michael Mui explain how Uber built an internal machine learning education program around Michelangelo, its machine learning platform. The program combines external... - [LangChain: Enabling LLMs to Use Tools](https://mlopstalks.com/talks/langchain-enabling-llms-to-use-tools): Harrison Chase, LangChain. Harrison Chase explains why language models need tools and how LangChain approaches the practical problems. Tools can provide current events, proprietary data, calculations, code execution,... - [Age of Industrialized AI](https://mlopstalks.com/talks/age-of-industrialized-ai): Dan Jeffries, AI Infrastructure Alliance. Dan Jeffries describes a future in which intelligent agents are embedded throughout software. He imagines small teams producing complex games because large thinking models coordinate... - [DevTools for Language Models: Unlocking the Future of AI-Driven Applications](https://mlopstalks.com/talks/devtools-for-language-models-unlocking-the-future-of-ai-driven-applications): Diego Oppenheimer, Factory. Diego Oppenheimer surveys the early LLM application stack and compares it with earlier waves of software and machine learning tooling. He describes a first version... - [The Birth and Growth of Spark: An Open Source Success Story](https://mlopstalks.com/talks/the-birth-and-growth-of-spark-an-open-source-success-story): Matei Zaharia, Databricks and Stanford. Matei Zaharia describes how Spark began as a Berkeley PhD project focused on large-scale data processing. Existing systems such as Hadoop worked for web indexing,... - [Challenges and Opportunities in Building Data Science Solutions with LLMs](https://mlopstalks.com/talks/challenges-and-opportunities-in-building-data-science-solutions-with-llms): Pascal Brokmeier, McKinsey and Company & Daniel Herde & Viktoriia Oliinyk, QuantumBlack, AI by McKinsey. Pascal Brokmeier, Daniel Herde, and Viktoriia Oliinyk discuss what they learned while building LLM applications for clients. Pascal describes running large models across Kubernetes nodes... - [Solving the Last Mile Problem of Foundation Models with Data-Centric AI](https://mlopstalks.com/talks/solving-the-last-mile-problem-of-foundation-models-with-data-centric-ai): Alex Ratner, Snorkel AI and University of Washington. Alex Ratner argues that foundation models are the base layer of AI applications, rather than complete products. Their broad capabilities work well for generic tasks... - [Vector Databases and Large Language Models](https://mlopstalks.com/talks/vector-databases-and-large-language-models): Samuel Partee, Redis. Samuel Partee explains how vector embeddings and vector databases extend large language models beyond the information in their training data. Embeddings represent unstructured data as... - [Want High Performing LLMs? Hint: It Is All About Your Data](https://mlopstalks.com/talks/want-high-performing-llms-hint-it-is-all-about-your-data): Vikram Chatterji, Galileo. Vikram Chatterji argues that the current LLM cycle resembles earlier waves of machine learning. AlexNet and Transformers brought major attention, models became easier to reuse,... - [Declarative MLOps: Streamlining Model Serving on Kubernetes](https://mlopstalks.com/talks/declarative-mlops-streamlining-model-serving-on-kubernetes): Rahul Parundekar, A.I. Hero, Inc.. Rahul Parundekar explains how Kubernetes can provide a repeatable way to package and serve machine learning models. Declarative MLOps means describing the desired deployment, such... - [ML Scalability Challenges](https://mlopstalks.com/talks/ml-scalability-challenges): Waleed Kadous, Anyscale. Waleed Kadous describes scalability as a problem that has followed machine learning throughout his career. He recalls distributing PhD experiments across 17 machines, scaling mapping... - [Tecton 0.6: Notebook-driven Development](https://mlopstalks.com/talks/tecton-0-6-notebook-driven-development): Jason Dunne, Tecton. Jason Dunne presents notebook-driven development in Tecton 0.6. He starts with the difficulty of building and maintaining real-time ML systems, using Uber Eats and fraud... - [Multilingual Programming and a Project Structure to Enable It](https://mlopstalks.com/talks/multilingual-programming-and-a-project-structure-to-enable-it): Rodolfo Núñez, Entel. Rodolfo Núñez explains why data scientists need basic software practices when their work must become a useful product. He argues for Git, clear names, reproducible... - [How A Manager Became a Believer in DevOps for Machine Learning](https://mlopstalks.com/talks/how-a-manager-became-a-believer-in-devops-for-machine-learning): Keith Trnka, 98.6. Keith Trnka describes how he moved from language modeling into broader machine learning and then into software engineering, operations, product context, and management. He says... - [Airflow Sucks for MLOps](https://mlopstalks.com/talks/airflow-sucks-for-mlops): Stephen Bailey, Whatnot. Stephen Bailey describes his work on Whatnot's data platform and explains why he thinks Airflow limits conversations about orchestration. Whatnot split its data platform, analytics,... - [ML in Production: A DS from Ubisoft Perspective](https://mlopstalks.com/talks/ml-in-production-a-ds-from-ubisoft-perspective): Jean-Michel Daignan, Ubisoft. Jean-Michel Daignan describes machine learning production work at Ubisoft from a data scientist's perspective. He explains how his earlier work in energy and proof-of-concept projects... - [Large Language Models in Production Round-table Conversation](https://mlopstalks.com/talks/large-language-models-in-production-round-table-conversation): Diego Oppenheimer, Factory HQ & David Hershey, Unusual Ventures & Hannes Hapke, Digits & James Richards, Bountiful & Rebecca Qian, Facebook AI Research. The panel discusses what it means to use large language models in production and where the difficult work begins. Rebecca Qian describes LLMs as a... - [The 7 Lines of Code You Need to Run Faster Real-time Inference](https://mlopstalks.com/talks/the-7-lines-of-code-you-need-to-run-faster-real-time-inference): Adrian Boguszewski, Intel. Adrian Boguszewski introduces OpenVINO, Intel's open-source toolkit for optimizing and deploying AI inference. He frames it as an option for teams that do not want... - [Let's Talk About Raw Documents](https://mlopstalks.com/talks/lets-talk-about-raw-documents): Crag Wolfe, Unstructured.io. Crag Wolfe presents Unstructured.io as an open-source library for turning raw documents into structured data for downstream machine learning work. The initial focus is on... - [Machine Learning Care](https://mlopstalks.com/talks/machine-learning-care): Matthew Dombrowski. Matthew Dombrowski describes the range of work involved in building and shipping machine learning products. He argues that the field is often reduced to data... - [MLOps vs ML-as-a-Service](https://mlopstalks.com/talks/mlops-vs-ml-as-a-service): Jill Chase & Manmeet Gujral, CapitalG. Jill Chase and Manmeet Gujral compare MLOps companies with ML-as-a-service and foundational model companies. Jill says MLOps revenue grows slowly because these businesses sell large... - [Team Aurora: Accelerating ML with Kubeflow](https://mlopstalks.com/talks/team-aurora-accelerating-ml-with-kubeflow): Maurizio Vitale, Vinay Anantharaman & Ankit Aggarwal, Aurora. Aurora's autonomous-vehicle workflow starts with vehicle logs, labeling, dataset creation, model training, evaluation, simulation, and deployment back to the vehicle. Before Kubeflow, many stages involved... - [The Motivation for MLOps](https://mlopstalks.com/talks/the-motivation-for-mlops): Steven Fines, CoreLogic. Steven Fines explains why machine learning becomes difficult to operate once several models reach production. Teams need to track model and pipeline versions, confirm that... - [Foundational Models are the Future but...](https://mlopstalks.com/talks/foundational-models-are-the-future-but): Alex Ratner, Snorkel AI. Alex Ratner explains why Snorkel AI focuses on data-centric development instead of treating model architecture as the main source of progress. He distinguishes active learning,... - [Vertex AI Workshop](https://mlopstalks.com/talks/vertex-ai-workshop): Sascha Heyer, DoiT. Sascha Heyer gives a hands-on introduction to using Vertex AI across model training, serving, and pipelines. He starts with a training application packaged in a... - [Explainability in the MLOps Cycle](https://mlopstalks.com/talks/explainability-in-the-mlops-cycle): Dattaraj Rao, Persistent. Dattaraj Rao explains how his work moved from mechanical engineering and rule-based monitoring systems at GE to computer vision, responsible AI, knowledge graphs, and MLOps... - [Machine Learning Operations: What Is It and Why Do We Need It?](https://mlopstalks.com/talks/machine-learning-operations-what-is-it-and-why-do-we-need-it): Niklas Kühl, IBM and Karlsruhe Institute of Technology (KIT). Niklas Kühl explains MLOps through the practical problem of turning machine learning work into products that create business value. He argues that the end goal... - [Building an Open Source MLOps Stack with ZenML Part 2](https://mlopstalks.com/talks/building-an-open-source-mlops-stack-with-zenml-part-2): Hamza Tahir, ZenML. Hamza Tahir explains why ZenML had to rebuild its architecture after early shortcuts created too much technical debt. The 0.20 release moved ZenML from a... - [Systems Engineer Navigating the World of ML](https://mlopstalks.com/talks/systems-engineer-navigating-the-world-of-ml): Andrew Dye, Union AI. Andrew Dye describes moving from low-level systems engineering on Microsoft's HoloLens to distributed training infrastructure at Meta and then to Union AI. His career brought... - ["Real-Time" ML: Features and Inference](https://mlopstalks.com/talks/real-time-ml-features-and-inference): Sasha Ovsankin & Rupesh Gupta, LinkedIn. Rupesh Gupta explains how recommender systems use recent user actions to infer changing intent and preferences. Batch pipelines can leave a delay of hours or... - [Building Threat Detection Systems: An MLE's Perspective](https://mlopstalks.com/talks/building-threat-detection-systems-an-mles-perspective): Jeremy Jordan, Duo Security. Jeremy Jordan discusses machine learning infrastructure for threat detection at Duo Security, drawing on earlier work at Proofpoint. He explains why rules remain useful in... - [Driving ML Data Quality with Data Contracts](https://mlopstalks.com/talks/driving-ml-data-quality-with-data-contracts): Andrew Jones, GoCardless. Andrew Jones describes how GoCardless moved away from copying upstream PostgreSQL databases into a central BigQuery warehouse through change data capture. That approach let upstream... - [MLOps in Practice: Common Challenges and Lessons Learned](https://mlopstalks.com/talks/mlops-in-practice-common-challenges-and-lessons-learned): Marouen Hizaoui & Mo Basirati, Machine Learning Reply. Marouen Hizaoui and Mo Basirati share project stories from insurance and retail clients with different levels of technical and MLOps maturity. They argue that MLOps... - [Real-time Machine Learning](https://mlopstalks.com/talks/real-time-machine-learning): Chip Huyen, Claypot AI. Chip Huyen explains how she learns by creating situations where she has to understand a subject well enough to teach or write about it. She... - [What is Data / ML Like on League?](https://mlopstalks.com/talks/what-is-data-ml-like-on-league): Ian Schweer, Riot Games. Ian Schweer describes the data and ML work behind League of Legends at Riot Games. League's game servers produce a compact, referentially complete record at... - [Creative AI: Using ML to Create Art, Music, and Jokes](https://mlopstalks.com/talks/creative-ai-using-ml-to-create-art-music-and-jokes): Suyash Joshi, MLOps Community. Suyash Joshi surveys creative uses of machine learning across image generation, music, humor, and storytelling. He compares GANs, variational autoencoders, flow-based models, and diffusion models,... - [Let's Continue Bundling into the Database](https://mlopstalks.com/talks/lets-continue-bundling-into-the-database): Ethan Rosenthal, Square. Ethan Rosenthal describes his work leading AI engineers on Square's Conversations Team, which builds smart features for Square Messages. His team develops chatbots and suggested... - [Unleashing Sensitive Datasets with Distributed Data Science](https://mlopstalks.com/talks/unleashing-sensitive-datasets-with-distributed-data-science): Blaise Thomson, Bitfount. Blaise Thomson explains how distributed data science lets teams work with medical, financial, and device data that cannot easily leave its current location. The basic... - [MLOps for Ad Platforms](https://mlopstalks.com/talks/mlops-for-ad-platforms): Andrew Yates, promoted.ai. Andrew Yates describes the engineering and organizational problems behind ad platforms at companies such as Facebook and Pinterest. Ads differ from ordinary recommendations because the... - [Applying DevOps Practices in Data and ML Engineering](https://mlopstalks.com/talks/applying-devops-practices-in-data-and-ml-engineering): Antoni Ivanov, VMWare. Antoni Ivanov describes a tension between operations teams, which manage infrastructure and reliability, and data teams, which need to deliver analytics and models quickly. He... - [Voice and Language Tech](https://mlopstalks.com/talks/voice-and-language-tech): Catherin Breslin, Kingfisher Labs. Catherin Breslin explains how speech and language technology has changed from a specialist field with custom tools into a more accessible part of machine learning.... - [Managing Machine Learning Projects](https://mlopstalks.com/talks/managing-machine-learning-projects): Simon Thompson, GFT. Simon Thompson discusses the work around machine learning that sits outside choosing and running algorithms. He argues that project managers should first understand the business... - [Obtain New Insights on Model Behavior with Fiddler](https://mlopstalks.com/talks/obtain-new-insights-on-model-behavior-with-fiddler): Danny Brock, Fiddler AI. Danny Brock presents Fiddler as a Model Performance Management platform that works alongside an existing machine learning stack. He explains how teams can monitor data... - [Reliable Machine Learning](https://mlopstalks.com/talks/reliable-machine-learning): Niall Murphy, Stanza Systems & Todd Underwood, Google. Niall Murphy and Todd Underwood discuss the ideas behind their book Reliable Machine Learning with David Aponte. They describe machine learning as an organizational change... - [ML Unicorn Start-up Investor Tells-IT-All](https://mlopstalks.com/talks/ml-unicorn-start-up-investor-tells-it-all): George Mathew, Insight Partners. George Mathew explains how he views the MLOps investment space from his role as a managing director at Insight Partners and from his earlier work... - [Databricks Model Serving V2](https://mlopstalks.com/talks/databricks-model-serving-v2): Rafael Pierre, Databricks. Rafael Pierre describes his path from software engineering in Brazil's stock exchange to data-intensive systems, machine learning, and his work at Databricks. He recalls building... - [Monitoring Unstructured Data](https://mlopstalks.com/talks/monitoring-unstructured-data): Aparna Dhinakaran & Jason Lopatecki, Arize AI. Jason Lopatecki and Aparna Dhinakaran explain why monitoring unstructured data is difficult. Production inputs can change without the team noticing, and the data is often... - [Trustworthy Machine Learning](https://mlopstalks.com/talks/trustworthy-machine-learning): Kush Varshney, IBM Research. Kush Varshney explains trustworthy machine learning as a way of working across the entire ML lifecycle. It begins with deciding whether a problem should be... - [Recommender System: Why They Update Models 100 Times a Day](https://mlopstalks.com/talks/recommender-system-why-they-update-models-100-times-a-day): Gleb Abroskin, FunCorp. Gleb Abroskin describes the recommender system behind FunCorp's iFunny app, where user-generated meme content changes quickly and models need frequent updates. A small engineering group... - [Scaling Similarity Learning at Digits](https://mlopstalks.com/talks/scaling-similarity-learning-at-digits): Hannes Hapke, Digits Financial, Inc.. Hannes Hapke explains how Digits uses machine learning to process accounting data for small businesses and give accountants a more current view of their books.... - [Bringing DevOps Agility to ML](https://mlopstalks.com/talks/bringing-devops-agility-to-ml): Luis Ceze, OctoML. Luis Ceze explains why he objects to using MLOps as a label for every part of machine learning delivery. Once a model is ready to... - [Feathr: LinkedIn's High-performance Feature Store](https://mlopstalks.com/talks/feathr-linkedins-high-performance-feature-store): David Stein, LinkedIn. David Stein explains how Feathr grew from an internal LinkedIn project into an open source feature store. LinkedIn had already been running recommendation, advertising, notification,... - [MLOps at DoorDash](https://mlopstalks.com/talks/mlops-at-doordash): Hien Luu & DoorDash Leads, DoorDash. Hien Luu and the DoorDash Leads describe a machine learning platform built for logistics, search, recommendations, advertising, forecasting, fraud, and delivery estimates. The platform covers... - [ML Platforms, Where to Start?](https://mlopstalks.com/talks/ml-platforms-where-to-start): Olalekan Elesin, HRS Product Solutions GmbH. Olalekan Elesin describes how he moved from engineering into technical product management while building an AI platform at Scout24. The team began with discovery because... - [From Expectations to Synthetic Data Generation](https://mlopstalks.com/talks/from-expectations-to-synthetic-data-generation): Fabiana Clemente, YData. Fabiana Clemente presents a hands-on workflow for generating and checking synthetic tabular data. She combines YData Synthetic for GAN-based generation, pandas-profiling for exploratory analysis, and... - [Data Engineering for ML](https://mlopstalks.com/talks/data-engineering-for-ml): Chad Sanderson, Convoy. Chad Sanderson explains why data modeling matters for machine learning and business analysis. He separates the physical model, which describes how data is stored in... - [Scaling Machine Learning with Data Mesh](https://mlopstalks.com/talks/scaling-machine-learning-with-data-mesh): Shawn Kyzer, Thoughtworks. Shawn Kyzer explains how Data Mesh principles can apply to machine learning projects. Data products began as curated, discoverable, trustworthy outputs for analytics, but machine... - [How Hera is an Enabler of MLOps Integrations](https://mlopstalks.com/talks/how-hera-is-an-enabler-of-mlops-integrations): Flaviu Vadan, Dyno Therapeutics. Flaviu Vadan explains how Dyno Therapeutics combines machine learning, lab experiments, and biological expertise to design better gene therapy vectors. The company works with adeno-associated... - [Product Enrichment and Recommender Systems](https://mlopstalks.com/talks/product-enrichment-and-recommender-systems): Marc Lindner & Amr Mashlah, eezylife Inc.. Marc Lindner and Amr Mashlah describe how eezylife builds recommendations across movies, restaurants, recipes, museums, concerts, and other activities. The product collects catalog data from... - [Building Better Data Teams](https://mlopstalks.com/talks/building-better-data-teams): Leanne Fitzpatrick, Financial Times. Leanne Fitzpatrick discusses how to build data teams when budgets, existing architecture, and business maturity constrain the options. She argues that leaders should start with... - [MLflow Pipelines: Opinionated ML Pipelines in MLflow](https://mlopstalks.com/talks/mlflow-pipelines-opinionated-ml-pipelines-in-mlflow): Xiangrui Meng, Databricks. Xiangrui Meng describes how his work moved from scalable algorithms in Spark MLlib to the wider problem of making machine learning usable in production. He... - [Argo Workflows](https://mlopstalks.com/talks/argo-workflows): Kemal Tugrul Yesilbek, Beat. Kemal Tugrul Yesilbek presents Argo Workflows as a Kubernetes-native system for running containerized workflows. Workflow definitions use YAML and specify metadata, templates, commands, images, and... - [Turning Redis into a Composable, ML Data Platform](https://mlopstalks.com/talks/turning-redis-into-a-composable-ml-data-platform): Samuel Partee, Redis. Samuel Partee explains how Redis is expanding from a web cache into a platform for ML serving. He describes Redis modules for JSON, search, and... - [Just Fetch the Data and then...](https://mlopstalks.com/talks/just-fetch-the-data-and-then): David Bayliss, LexisNexis Risk Solutions. David Bayliss describes the data infrastructure behind LexisNexis Risk Solutions, where information is used for identity checks, credit, insurance, fraud detection, background checks, and other... - [So Fresh and So Data Clean](https://mlopstalks.com/talks/so-fresh-and-so-data-clean): Tommy Dang, Mage. Tommy Dang introduces Mage, an open source code editor for transforming data and building machine learning pipelines. He demonstrates a Titanic pipeline that loads data,... - [Why You Need More Than Airflow](https://mlopstalks.com/talks/why-you-need-more-than-airflow): Ketan Umare, Union.ai. Ketan Umare explains why machine learning workflows need different infrastructure from traditional software and data pipelines. Models can become invalid when external conditions change, as... - [DevOps, Security, and Observability in ML](https://mlopstalks.com/talks/devops-security-and-observability-in-ml): Luke Marsden, MLOps Consulting. Luke Marsden explains how to assemble an MLOps stack from a large and changing set of tools. He starts with the basic flow from data... - [MLflow vs Kubeflow 2022](https://mlopstalks.com/talks/mlflow-vs-kubeflow-2022): Byron Allen, Contino. Byron Allen and George Pearse revisit MLflow and Kubeflow two years after their earlier discussion. Allen describes MLflow as a lightweight package focused mainly on... - [Code Quality in Data Science](https://mlopstalks.com/talks/code-quality-in-data-science): Laszlo Sragner, Hypergolic. Laszlo Sragner explains why machine learning products need software engineering practices. These products often have long lifespans, solve fuzzy business problems, and change while they... - [Why and When to Use Kubeflow for MLOps](https://mlopstalks.com/talks/why-and-when-to-use-kubeflow-for-mlops): Ryan Russon, Maven Wave Partners. Ryan Russon argues that Kubeflow makes sense when a company is already Kubernetes-oriented. It provides notebook-based exploration, pipeline orchestration, and model serving in an open-source... - [Speed Up Data-Driven Value](https://mlopstalks.com/talks/speed-up-data-driven-value): Delina Ivanova, HelloFresh. Delina Ivanova describes how she moved from finance and consulting into data leadership at HelloFresh. Her earlier work in forecasting, operations, strategy, data governance, and... - [Labeled Datasets that Correct Themselves Automatically](https://mlopstalks.com/talks/labeled-datasets-that-correct-themselves-automatically): Curtis Northcutt, Cleanlab. Curtis Northcutt explains how his work on cheating detection for MIT and Harvard online courses led to Cleanlab. The cheating problem was a noisy-label problem... - [FLOps with Scaleout's Open-core Platform](https://mlopstalks.com/talks/flops-with-scaleouts-open-core-platform): Marco Capuccini, Scaleout Systems. Marco Capuccini explains why some machine learning systems should move computation to data instead of collecting all data in a central store. Federated learning lets... - [MLOps + BI?](https://mlopstalks.com/talks/mlops-bi): Maxime Beauchemin, Preset. Maxime Beauchemin explains why the data warehouse has become a natural home for analytics and some machine learning work. Data wants to be brought together,... - [The Post Modern Stack](https://mlopstalks.com/talks/the-post-modern-stack): Jacopo Tagliabue, Coveo. Jacopo Tagliabue presents a streamlined alternative to the larger MLOps stacks often shown by major technology companies. His example uses Snowflake and dbt to turn... - [Making MLflow](https://mlopstalks.com/talks/making-mlflow): Corey Zumar, Databricks. Corey Zumar explains how MLflow started at Databricks as an open-source response to a fragmented machine learning tooling ecosystem. Existing platforms often focused on one... - [Building a Movie Recommendation System on Tecton with Snowflake](https://mlopstalks.com/talks/building-a-movie-recommendation-system-on-tecton-with-snowflake): David Hershey, Tecton. David Hershey demonstrates an end-to-end movie recommendation system built with Tecton and Snowflake. The system starts with daily, precomputed recommendations for each user. Movie metadata... - [Fixing Your ML Data Blind Spots](https://mlopstalks.com/talks/fixing-your-ml-data-blind-spots): Yash Sheth, Galileo. Yash Sheth explains why data work is often the hardest part of building machine learning systems with unstructured data. From his experience leading speech recognition... - [Declarative Machine Learning Systems: Big Tech Level ML Without a Big Tech Team](https://mlopstalks.com/talks/declarative-machine-learning-systems-big-tech-level-ml-without-a-big-tech-team): Piero Molino, Predibase. Piero Molino explains why he built Predibase around declarative machine learning. At Uber, he saw teams rewrite bespoke code for each project, creating technical debt... - [On Juggling, Dr. Seuss and Feature Stores for Real-time AI/ML](https://mlopstalks.com/talks/on-juggling-dr-seuss-and-feature-stores-for-real-time-ai-ml): Nava Levy, Redis. Nava Levy explains why real-time machine learning becomes difficult when a prediction must use fresh data inside an interactive application. A 100-millisecond end-to-end target may... - [MLOps Critiques](https://mlopstalks.com/talks/mlops-critiques): Matthijs Brouns, Xccelerated.io. Matthijs Brouns describes MLOps as a field where standard answers are still hard to find. His experience with a client that grew from about 3,000... - [Scaling Real-time Machine Learning at Chime](https://mlopstalks.com/talks/scaling-real-time-machine-learning-at-chime): Peeyush Agarwal, Chime. Peeyush Agarwal describes how Chime built infrastructure for real-time machine learning, using fraud detection in its Pay Friends product as the first detailed example. Chime's... - [GPU For Machine Learning](https://mlopstalks.com/talks/gpu-for-machine-learning): Ronen Dar & Gijsbert Janssen van Doorn, Run:ai. Ronen Dar and Gijsbert Janssen van Doorn explain why Run:ai was built around GPU resource management for machine learning. Ronen describes a gap between compute-intensive... - [DataOps is a Software Engineering Challenge](https://mlopstalks.com/talks/dataops-is-a-software-engineering-challenge): Micha Kunze, Maersk. Micha Kunze describes how Maersk's forecasting team operates five machine learning products that produce about 3 million forecasts each day. The team has to work... - [Real-time Model Inference in a Video Streaming Environment](https://mlopstalks.com/talks/real-time-model-inference-in-a-video-streaming-environment): Brannon Dorsey, Runway. Brannon Dorsey describes Runway as a web-based video editor with machine learning tools for tasks such as rotoscoping, inpainting, and audio cleanup. The company began... - [The Role of Resource Management in MLOps](https://mlopstalks.com/talks/the-role-of-resource-management-in-mlops): Ronen Dar & Gijsbert Janssen van Doorn, Run:AI. Ronen Dar and Gijsbert Janssen van Doorn argue that resource management is an overlooked part of MLOps. Teams often focus on models, data, monitoring, and... - [Real-Time Processing with Apache Flink, Kafka, and Pinot](https://mlopstalks.com/talks/real-time-processing-with-apache-flink-kafka-and-pinot): Jacob Tsafatinos, Elemy. Jacob Tsafatinos discusses the real-time ad event processing system he helped build at Uber. The system handled events from ads and supported data scientists, billing,... - [FastAPI for Machine Learning](https://mlopstalks.com/talks/fastapi-for-machine-learning): Sebastián Ramírez, Forethought. Sebastián Ramírez explains FastAPI as a Python framework for web APIs built around type annotations and current Python features, including optional async support. FastAPI uses... - [MLOps EngineeringLabs](https://mlopstalks.com/talks/mlops-engineeringlabs): Niels Bantilan & Haytham Abuelfutuh, Union.Ai. Haytham Abuelfutuh introduces Flyte as a Kubernetes-native workflow automation platform for business-critical machine learning and data processing. He explains how tasks and workflows use typed... - [MLOps as Tool to Shape Team and Culture](https://mlopstalks.com/talks/mlops-as-tool-to-shape-team-and-culture): Ciro Greco, Coveo. Ciro Greco describes his move from cognitive science research into NLP, entrepreneurship, and his role as VP of AI at Coveo. Coveo supports search and... - [Traversing the Data Maturity Spectrum: A Startup Perspective](https://mlopstalks.com/talks/traversing-the-data-maturity-spectrum-a-startup-perspective): Mark Freeman, Humu. Mark Freeman explains why companies cannot jump directly from hiring data scientists to running machine learning in production. Data maturity develops through stages, beginning with... - [Modern Data Science with Vaex](https://mlopstalks.com/talks/modern-data-science-with-vaex): Maarten Breddels, Vaex.io & Jovan Veljanoski, Tiqets. Maarten Breddels and Jovan Veljanoski introduce Vaex, an open-source Python DataFrame library for datasets that do not fit in memory. Vaex uses memory-mapped files, column-based... - [Model Monitoring in Practice: Top Trends](https://mlopstalks.com/talks/model-monitoring-in-practice-top-trends): Krishnaram Kenthapadi, Fiddler AI. Krishnaram Kenthapadi explains why model monitoring belongs inside a broader responsible AI and governance process. Before deployment, teams validate models and inspect their explanations. After... - [Building the World's First Data Engineering Conference](https://mlopstalks.com/talks/building-the-worlds-first-data-engineering-conference): Pete Soderling, Data Council and Data Community Fund. Pete Soderling describes how Data Council began as a 2013 meetup inside Spotify's New York office and grew into a conference covering data infrastructure, data... - [The Shipyard: Lessons Learned While Building an ML Platform](https://mlopstalks.com/talks/the-shipyard-lessons-learned-while-building-an-ml-platform): Joseph Haaga, Interos. Joseph Haaga explains how Interos built an internal ML platform for models that read supply-chain news, extract events and relationships, and resolve entities into a... - [Bringing Audio ML Models into Production](https://mlopstalks.com/talks/bringing-audio-ml-models-into-production): Valerio Velardo, Utopia Music. Valerio Velardo explains why audio ML has different production needs from image and language work. Music, environmental sound, and speech are related areas, but each... - [A Journey in Scaling ML](https://mlopstalks.com/talks/a-journey-in-scaling-ml): Gabriel Straub, Ocado Technology. Gabriel Straub describes how Ocado Technology built its own technology for online grocery because existing systems did not fit the business. The company now develops... - [ML Platform Tradeoffs and Wondering Why to Use Them](https://mlopstalks.com/talks/ml-platform-tradeoffs-and-wondering-why-to-use-them): Javier Mansilla, Mercado Libre. Javier Mansilla describes Mercado Libre as an e-commerce, fintech, advertising, credit, and logistics ecosystem serving Latin America. Its ML platform team builds shared foundations for... - [Building a Modern Data Analytics Stack](https://mlopstalks.com/talks/building-a-modern-data-analytics-stack): Jeff Katz, Jigsaw Labs. Jeff Katz demonstrates an end-to-end analytics and machine learning workflow built around Mixpanel, Fivetran, BigQuery, dbt, and BigQuery ML. A website sends page views and... - [Don't Listen Unless You Are Going to Do ML in Production](https://mlopstalks.com/talks/dont-listen-unless-you-are-going-to-do-ml-in-production): Kyle Morris, banana.dev. Kyle Morris describes banana.dev as a way to move a trained model into production without making every data scientist learn infrastructure operations. The service accepts... - [Applications of Data Science](https://mlopstalks.com/talks/applications-of-data-science): Connie Yang, Pallet. Connie Yang explains how data science fits into a product that already has business, engineering, and operational constraints. She focuses on the work after model... - [Building ML/Data Platform on Top of Kubernetes](https://mlopstalks.com/talks/building-ml-data-platform-on-top-of-kubernetes): Julien Bisconti. Julien Bisconti discusses the practical work behind building an ML and data platform on Kubernetes. He argues that code is often easier to change than... - [Machine Learning Engineering in Action](https://mlopstalks.com/talks/machine-learning-engineering-in-action): Ben Wilson. Machine Learning Engineering in Action is the book Ben Wilson discusses in this reading group. Wilson presents the book as a record of mistakes and... - [MLOps at Stripe](https://mlopstalks.com/talks/mlops-at-stripe): Emmanuel Ameisen, Stripe. Emmanuel Ameisen describes the operational work required after a machine learning model becomes part of a real product. At Stripe, his team works on Stripe... - [Orchestrating Machine Learning Workflows with Prefect](https://mlopstalks.com/talks/orchestrating-machine-learning-workflows-with-prefect): Kevin Kho, Prefect. Kevin Kho introduces workflow orchestration through a machine learning pipeline that pulls data from a database and API, transforms it, trains a model, records artifacts,... - [Lessons from Studying FAANG ML Systems](https://mlopstalks.com/talks/lessons-from-studying-faang-ml-systems): Ernest Chan, Duo Security. Ernest Chan explains what he learned by studying ML systems at companies including Netflix, DoorDash, Spotify, Uber, PayPal, and Intuit. His interest started after helping... - [Better Use Cases for Text Embeddings](https://mlopstalks.com/talks/better-use-cases-for-text-embeddings): Vincent Warmerdam, Explosion. Vincent Warmerdam talks about how machine learning systems fail, why teams should understand their data before selecting models, and how simpler methods can be easier... - [Feature Stores at Shopify and Skyscanner](https://mlopstalks.com/talks/feature-stores-at-shopify-and-skyscanner): Matt Delacour, Shopify & Mike Moran, Skyscanner. This reading group did not discuss a paper or book chapter; Matt Delacour and Mike Moran presented how Shopify and Skyscanner built feature store systems.... - [Trustworthy Data for Machine Learning](https://mlopstalks.com/talks/trustworthy-data-for-machine-learning): Chad Sanderson, Convoy. Chad Sanderson describes Convoy's shift from rapid model deployment toward data quality. Convoy uses machine learning for pricing, ETA prediction, offer relevance, and simulation in... - [Practitioners Guide to MLOps](https://mlopstalks.com/talks/practitioners-guide-to-mlops): Donna Schut & Christos Aniftos, Google Cloud. Donna Schut and Christos Aniftos explain how Google Cloud developed the Practitioners' Guide to MLOps from repeated customer questions. The guide describes six connected processes,... - [Investing in MLOps](https://mlopstalks.com/talks/investing-in-mlops): Leigh Marie Braswell, Founders Fund & Davis Treybig, Innovation Endeavors. Leigh Marie Braswell and Davis Treybig discuss machine learning companies from an investor's perspective. They describe MLOps infrastructure as crowded, with teams often stitching together... - [The Journey from Data Scientist to MLOps Engineer](https://mlopstalks.com/talks/the-journey-from-data-scientist-to-mlops-engineer): Ale Solano. Ale Solano describes how he moved from data science toward MLOps after years of building proof-of-concepts that produced no business value. He worked at a... - [Platform Thinking: A Lemonade Case Study](https://mlopstalks.com/talks/platform-thinking-a-lemonade-case-study): Orr Shilon, Lemonade. Orr Shilon describes how Lemonade built an internal machine learning platform around early engineering involvement, automation, and clear ownership. Data scientists can explore data in... - [Building an Open Source MLOps Stack with ZenML](https://mlopstalks.com/talks/building-an-open-source-mlops-stack-with-zenml): Hamza Tahir, ZenML. Hamza Tahir introduces ZenML through a live NBA example. The pipeline compares basketball data before and after Stephen Curry's change in three-point strategy, then uses... - [Calibration for ML at Etsy](https://mlopstalks.com/talks/calibration-for-ml-at-etsy): Erica Greene & Seoyoon Park, Etsy. Erica Greene and Seoyoon Park explain how Etsy added calibration to its machine learning workflow for ad ranking. Their click-through-rate model trained on downsampled data,... - [Data Mesh: Data Quality Control Mechanism for MLOps?](https://mlopstalks.com/talks/data-mesh-data-quality-control-mechanism-for-mlops): Scott Hirleman, DataStax. Scott Hirleman explains data mesh as a way to organize analytical data around data products owned by business domains. A data product includes the raw... - [Build a Culture of ML Testing and Model Quality](https://mlopstalks.com/talks/build-a-culture-of-ml-testing-and-model-quality): Mohamed Elgendy, Kolena. Mohamed Elgendy explains why model quality cannot be captured by a single accuracy or F1 score. He draws on work with computer-vision systems, including a... - [Towards Observability for ML Pipelines](https://mlopstalks.com/talks/towards-observability-for-ml-pipelines): Shreya Shankar, UC Berkeley. Shreya Shankar describes how her work across Google Brain, an early-stage startup, and UC Berkeley shaped her view of ML systems. She separates infrastructure problems,... - [Scaling Biotech](https://mlopstalks.com/talks/scaling-biotech): Jesse Johnson, Dewpoint Therapeutics. Jesse Johnson describes how his path from academic mathematics led through software engineering, healthcare data, drug discovery, and biotech research. He explains why building useful... - [Federated Learning: Machine Learning on the Edge](https://mlopstalks.com/talks/federated-learning-machine-learning-on-the-edge): Varun Kumar Khare, Nimble Edge. The reading group discusses the paper "Federated Learning: Strategies for Improving Communication Efficiency" and the earlier introduction of federated learning by Brendan McMahan and others.... - [Just Build It! Tips for Making ML Engineering and MLOps Real](https://mlopstalks.com/talks/just-build-it-tips-for-making-ml-engineering-and-mlops-real): Andy McMahon, NatWest Group. Andy McMahon argues that teams should start building ML engineering and MLOps capability before they feel fully ready. He separates ML engineering, which applies software... - [On Structuring an ML Platform 1 Pizza Team](https://mlopstalks.com/talks/on-structuring-an-ml-platform-1-pizza-team): Breno Costa & Matheus Frata, Neoway. Breno Costa and Matheus Frata describe how Neoway created a machine learning platform team during a wider organizational redesign. The company had previously grouped people... - [2021 MLOps Year in Review](https://mlopstalks.com/talks/2021-mlops-year-in-review): Vishnu Rachakonda, Tesseract Health & Demetrios Brinkmann, MLOps Community. Vishnu Rachakonda and Demetrios Brinkmann review the MLOps Community and ecosystem at the end of 2021. They discuss the community's growth, including the gap between... - [Setting up an ML Platform on GCP: Lessons Learned](https://mlopstalks.com/talks/setting-up-an-ml-platform-on-gcp-lessons-learned): Mefta Sadat, Loblaw Digital. Mefta Sadat describes how Loblaw Digital built an ML and data platform for production systems in search, recommendations, inventory, labor forecasting, and other grocery use... - [2022 Predictions for MLOps and the Industry](https://mlopstalks.com/talks/2022-predictions-for-mlops-and-the-industry): Reah Miyara, Arize AI. Reah Miyara gives several predictions for MLOps in 2022 in conversation with Demetrios Brinkmann. He expects AI fairness and bias issues to get worse before... - [Building 12-Factor Data Apps with Kedro](https://mlopstalks.com/talks/building-12-factor-data-apps-with-kedro): Ivan Danov, QuantumBlack. Ivan Danov argues that data teams are repeating problems the web software industry faced during its rapid growth. One-off analyses are becoming machine learning products... - [Building for Small Data Science Teams](https://mlopstalks.com/talks/building-for-small-data-science-teams): James Lamb, SpotHero. James Lamb describes how SpotHero is designing machine learning infrastructure for a small data science team. When he joined, four data scientists and a small... - [Modern ML Stack is a Lie](https://mlopstalks.com/talks/modern-ml-stack-is-a-lie): Mike Del Balso, Tecton & Joe Reis. Mike Del Balso and Joe Reis discuss why the modern ML stack has not settled into a clear set of composable services. Data teams have... - [ML Drift: How to Identify Issues Before They Become Problems](https://mlopstalks.com/talks/ml-drift-how-to-identify-issues-before-they-become-problems): Amy Hodler, Fiddler. Amy Hodler explains model drift as predictions getting worse over time. She separates the way drift appears, such as abrupt, gradual, periodic, or isolated changes,... - [Wikimedia MLOps](https://mlopstalks.com/talks/wikimedia-mlops): Chris Albon, Wikimedia Foundation. Chris Albon describes how Wikimedia's six-person machine learning team supports models used across the Foundation. These models predict article quality, flag potentially damaging edits, and... - [The ML Test Score](https://mlopstalks.com/talks/the-ml-test-score): Skylar Payne. The paper The ML Test Score: A Rubric for ML Production Readiness and Technical Debt Reduction proposes a checklist for assessing whether machine learning systems... - [ML Stepping Stones: Challenges & Opportunities for Companies](https://mlopstalks.com/talks/ml-stepping-stones-challenges-opportunities-for-companies): John Crousse. John Crousse describes what changes when companies build machine learning products instead of isolated projects. A model is usually one part of a larger system,... - [Machine Learning at Reasonable Scale](https://mlopstalks.com/talks/machine-learning-at-reasonable-scale): Jacopo Tagliabue, Coveo. Jacopo Tagliabue argues that most machine learning teams are learning from companies operating at a scale they will never need. The practical problem for many... - [The Not So Talked About Reasons Model Monitoring Fails](https://mlopstalks.com/talks/the-not-so-talked-about-reasons-model-monitoring-fails): Oren Razon, Superwise. Oren Razon argues that model monitoring becomes difficult when machine learning moves from experimentation into business operations. Technical monitoring of drift, data quality, inputs, outputs,... - [The Future of Data Science Platforms is Accessibility](https://mlopstalks.com/talks/the-future-of-data-science-platforms-is-accessibility): Skylar Payne. Skylar Payne argues that data science platforms have become too complex for the people expected to use them. Teams adopt tools such as Kubeflow because... - [Model Monitoring: The Million Dollar Problem](https://mlopstalks.com/talks/model-monitoring-the-million-dollar-problem): . The Loka Team explains why machine learning models can lose performance after deployment. COVID-19 changed usage patterns, supply chains, and data distributions, so models trained... - [Impact of SWE in ML Projects](https://mlopstalks.com/talks/impact-of-swe-in-ml-projects): Laszlo Sragner & Tim Blazina. The discussion covers the book "Object Design Style Guide" and applies its software design ideas to machine learning projects. Laszlo Sragner and Tim Blazina argue... - [The Future of AI and ML in Process Automation](https://mlopstalks.com/talks/the-future-of-ai-and-ml-in-process-automation): Slater Victoroff, Indico Data. Slater Victoroff describes how his early work with traditional machine learning led him to focus on making deep learning usable in enterprises. He defines unstructured... - [Durable Data Discovery: Making Exploratory Analysis Stick](https://mlopstalks.com/talks/durable-data-discovery-making-exploratory-analysis-stick): James Campbell, Superconductive. James Campbell argues that exploratory data analysis often contains knowledge that disappears when a project moves into production or changes hands. Great Expectations can preserve... - [PyTorch: Bridging AI Research and Production](https://mlopstalks.com/talks/pytorch-bridging-ai-research-and-production): Dmytro Dzhulgakov, Facebook. Dmytro Dzhulgakov discusses how he moved from infrastructure work at Facebook into machine learning tooling and became a technical lead for PyTorch. He explains that... - [Data-Centric AI Means Centralizing Training Data](https://mlopstalks.com/talks/data-centric-ai-means-centralizing-training-data): Alberto Rizzoli, V7. Alberto Rizzoli argues that computer vision teams are gaining more from improving training data than from repeatedly changing model architectures. Companies need to capture knowledge... - [I Don't Like Jupyter Notebooks](https://mlopstalks.com/talks/i-dont-like-jupyter-notebooks): Joel Grus, Capital Group. Joel Grus explains how he moved from mathematics and quantitative finance into data science, software engineering, and machine learning engineering. He revisits his 2018 JupyterCon... - [MLOps at Volvo Cars](https://mlopstalks.com/talks/mlops-at-volvo-cars): Leonard Aukea, Volvo Cars. Leonard Aukea presents Volvo Cars' approach to building a machine learning platform for enterprise use. The company runs dedicated machine learning clusters on Kubernetes and... - [ML Tests](https://mlopstalks.com/talks/ml-tests): Svet Penkov, Efemarai. Svet Penkov describes ML testing as a quality assurance problem that starts before deployment. His robotics work showed him that real-world systems cannot simply be... - [LinkedIn Job Recommendations](https://mlopstalks.com/talks/linkedin-job-recommendations): Alexandre Patry, LinkedIn. Alexandre Patry describes how LinkedIn's job recommendation team changed its models, processes, and measures after large personalized models became difficult to operate. The team moved... - [End to End MLOps Basics](https://mlopstalks.com/talks/end-to-end-mlops-basics): Raviraja Ganta, Enterpret. Raviraja Ganta explains MLOps through the lifecycle of an ML system, starting with development and ending with monitoring in production. He argues that training is... - [Feast Feature Store Deep Dive](https://mlopstalks.com/talks/feast-feature-store-deep-dive): Felix Wang, Tecton. Felix Wang introduces Feast through a real-time credit-scoring tutorial running on AWS. The example trains a model to decide whether a loan should be approved,... - [Doing MLOps](https://mlopstalks.com/talks/doing-mlops): Noah Gift, Pragmatic AI Labs. Noah Gift explains MLOps as the work of getting a machine learning model into production and keeping it useful after deployment. He describes a layered... - [Data Selection for Data-Centric AI: Data Quality Over Quantity](https://mlopstalks.com/talks/data-selection-for-data-centric-ai-data-quality-over-quantity): Cody Coleman. Cody Coleman describes why machine learning should focus more on data quality and selection. He connects this view to his work on DAWNBench and MLPerf,... - [The Future of ML and Data Platforms](https://mlopstalks.com/talks/the-future-of-ml-and-data-platforms): Michael Del Balso, Tecton. Michael Del Balso and Erik Bernhardsson discuss how data platforms, ML systems, and software engineering are converging. They argue that companies should avoid building large... - [A Few Learnings from Building a Bootstrapped MLOps Services Startup](https://mlopstalks.com/talks/a-few-learnings-from-building-a-bootstrapped-mlops-services-startup): Soumanta Das, Yugen.ai. Soumanta Das describes how Yugen.ai grew from two people starting during the early months of the pandemic to a team working on ranking, recommendations, replenishment,... - [Engineering Best Practices for Machine Learning](https://mlopstalks.com/talks/engineering-best-practices-for-machine-learning): Alex Serban, Radboud University. Alex Serban presents research into engineering practices for software that contains machine learning components. His team reviewed academic and industry literature, organized the findings into... - [Learning and Teaching MLOps Applications](https://mlopstalks.com/talks/learning-and-teaching-mlops-applications): Salwa Muhammad, FourthBrain. Salwa Muhammad describes how her background in higher education and edtech led her to found FourthBrain, a program intended to bring more people into machine... - [System Design for Recommendations and Search](https://mlopstalks.com/talks/system-design-for-recommendations-and-search): Eugene Yan, Amazon. Eugene Yan explains recommendation and search systems through two divisions: offline versus online computation, and candidate retrieval versus ranking. Batch systems precompute recommendations and store... - [Moldable Development with Glamorous Toolkit](https://mlopstalks.com/talks/moldable-development-with-glamorous-toolkit): Tudor Gîrba, Feenk. Tudor Gîrba argues that code reading remains an unexamined source of waste in software development. Developers read code because they need information for decisions, so... - [Machine Learning SRE](https://mlopstalks.com/talks/machine-learning-sre): Niall Murphy, Microsoft Azure. Niall Murphy explains how site reliability engineering applies to machine learning systems. The basic responsibilities remain familiar: define acceptable service levels, measure production behavior, react... - [MLOps Insights](https://mlopstalks.com/talks/mlops-insights): David Aponte-Demetrios Brinkmann-Vishnu Rachakonda. This conversation covers practical testing and production work in machine learning. David Aponte explains that ML systems need more than unit tests. Teams may test... - [Vector Similarity Search at Scale](https://mlopstalks.com/talks/vector-similarity-search-at-scale): Dave Bergstein, Pinecone. Dave Bergstein explains how Pinecone provides managed vector similarity search for production applications. Neural networks can turn images or text into vectors whose distances capture... - [Building Machine Learning Models into Docker Images](https://mlopstalks.com/talks/building-machine-learning-models-into-docker-images): Luke Marsden, MLOps Consulting. Luke Marsden explains how to package a trained machine learning model and its serving code into a Docker image. He starts with a Flask server... - [mlctl and Hydrosphere Open Source MLOps Libraries Demo](https://mlopstalks.com/talks/mlctl-and-hydrosphere-open-source-mlops-libraries-demo): Alex Chung, Intuit. Alex Chung demonstrates mlctl, a library that gives data scientists and ML engineers templates for processing, training, and deployment code. The code is packaged into... - [What MLOps Has Taught Me](https://mlopstalks.com/talks/what-mlops-has-taught-me): Ewan Nicolson, Forecast. Ewan Nicolson uses a local recommender-system demo to explain what production machine learning demands. The system streams Amazon reviews into a data lake, cleans the... - [ML Security: Why should you care?](https://mlopstalks.com/talks/ml-security-why-should-you-care): Sahbi Chaieb, SAS. Sahbi Chaieb explains why machine learning security needs attention before a model reaches production. Machine learning systems inherit ordinary software and cybersecurity risks, then add... - [Creating MLOps Standards](https://mlopstalks.com/talks/creating-mlops-standards): Alex Chung, Social Good Technologies & Srivathsan Canchi, Intuit. Alex Chung and Srivathsan Canchi describe why enterprise ML teams struggle with tooling sprawl. A company may have many data science groups, each using different... - [Aggressively Helpful Platform Teams](https://mlopstalks.com/talks/aggressively-helpful-platform-teams): Stefan Krawczyk, Stitch Fix. Stefan Krawczyk describes how Stitch Fix supports more than 130 full-stack data scientists who build and own production data products. The Data Platform team tries... - [Building an ML Platform from Scratch: Live Coding Session - Part 2](https://mlopstalks.com/talks/building-an-ml-platform-from-scratch-live-coding-session-part-2): Alon Gubkin, Aporia. Alon Gubkin continues the platform built in the first workshop, where DVC handled data versioning, MLflow tracked experiments, and FastAPI served models. He adds model... - [The SAME Project: A Cloud Native Approach to Reproducible ML](https://mlopstalks.com/talks/the-same-project-a-cloud-native-approach-to-reproducible-ml): David Aronchick, Microsoft. David Aronchick presents SAME, the Self-Assembling Machine Learning Environment, as a way to move exploratory notebooks into reliable production workflows. He argues that forcing data... - [SGT Model Deployment Working Group](https://mlopstalks.com/talks/sgt-model-deployment-working-group): Srivathasan Canchi, Intuit. Srivathasan Canchi introduces mlctl, an open-source MLOps toolkit developed at Intuit. The library provides a common SDK and CLI for creating projects, packaging code, building... - [Tour of Upcoming Features on the Hugging Face Model Hub](https://mlopstalks.com/talks/tour-of-upcoming-features-on-the-hugging-face-model-hub): Julien Chaumond, Hugging Face. Julien Chaumond describes how Hugging Face developed from a small NLP company into an open-source community and model platform. The company began by releasing practical... - [Building ML Blocks with Kubeflow Orchestration with Feature Store](https://mlopstalks.com/talks/building-ml-blocks-with-kubeflow-orchestration-with-feature-store): Aniruddha Choudhury, Publicis Sapient. Aniruddha Choudhury walks through an end-to-end machine learning system built with Feast, Kubeflow, Kubernetes, Spark, Kafka, Redis, and Google Cloud. He starts with the problem... - [Orchestrating Spark Jobs with Kubeflow](https://mlopstalks.com/talks/orchestrating-spark-jobs-with-kubeflow): Sadik Bakiu, Freelance ML Engineer. Sadik Bakiu explains why a Spark job needs orchestration when data processing becomes part of a repeated machine learning workflow. He focuses on preprocessing, where... - [Fast.ai, AutoML, and Software Engineering for ML](https://mlopstalks.com/talks/fast-ai-automl-and-software-engineering-for-ml): Jeremy Howard, Fast.ai. Jeremy Howard explains how his experience with notebooks, software engineering, and machine learning shaped fast.ai and nbdev. He wants tools to match how people actually... - [Learning from 150 Successful ML-enabled Products at Booking.com](https://mlopstalks.com/talks/learning-from-150-successful-ml-enabled-products-at-booking-com): Pablo Estevez, Booking.com. Pablo Estevez explains how Booking.com studied about 150 successful customer-facing machine learning applications and the larger set of attempts that did not work. The company... - [Machine Learning in Cybersecurity](https://mlopstalks.com/talks/machine-learning-in-cybersecurity): Monika Venčkauskaitė, Vinted. Monika Venčkauskaitė explains how machine learning is used in cybersecurity and where it falls short. She describes the incident-response cycle, from identifying a threat through... - [Enterprise Security and Governance MLOps](https://mlopstalks.com/talks/enterprise-security-and-governance-mlops): Diego Oppenheimer, Algorithmia. Diego Oppenheimer explains why security and governance are often the longest part of putting machine learning into production. Operational ML systems run continuously inside an... - [Autonomy vs. Alignment: Scaling AI Teams to Deliver Value](https://mlopstalks.com/talks/autonomy-vs-alignment-scaling-ai-teams-to-deliver-value): Grant Wright, SEEK Ltd.. Grant Wright describes how SEEK built and scaled AI teams across its employment marketplace. The organization first had to teach people what AI could do... - [How Pinterest Powers Image Similarity](https://mlopstalks.com/talks/how-pinterest-powers-image-similarity): Shaji Chennan Kunnummel, Pinterest. Shaji Chennan Kunnummel explains Pinterest's near-real-time system for finding exact and near-duplicate images. A newly uploaded image is represented by embeddings, converted into LSH terms,... - [Engineering MLOps](https://mlopstalks.com/talks/engineering-mlops): Emmanuel Raj, TietoEvry. Emmanuel Raj explains MLOps as the use of software engineering and DevOps practices to build, deploy, and monitor machine learning systems. He connects project failures... - [SGT Model Deployment Working Group June 22, 2021 Meeting](https://mlopstalks.com/talks/sgt-model-deployment-working-group-june-22-2021-meeting): . The Social Good Tech model deployment working group compared two ways to test compliance with NVIDIA's v2 inference specification. Proposal one would provide protobufs, test... - [Project/Product Management for MLOps](https://mlopstalks.com/talks/project-product-management-for-mlops): Korri Jones-Simarpal Khaira-Veselina Staneva. The panel discusses how product and project managers can build MLOps capabilities that fit both present needs and future growth. Korri Jones argues that teams... - [Maturing Machine Learning in Enterprise](https://mlopstalks.com/talks/maturing-machine-learning-in-enterprise): Kyle Gallatin, Etsy. Kyle Gallatin describes his move from data analysis and data science into machine learning infrastructure, including the software engineering skills he had to learn along... - [Building an ML Platform from Scratch: Live Coding Session](https://mlopstalks.com/talks/building-an-ml-platform-from-scratch-live-coding-session): Alon Gubkin, Aporia. Alon Gubkin builds a small ML platform on AWS during a live coding workshop. He starts with the problems that grow when an organisation has... - [Practical MLOps Part 2](https://mlopstalks.com/talks/practical-mlops-part-2): Alfredo Deza, Author and Speaker. Alfredo Deza explains MLOps through the practices he learned from DevOps and software engineering. He says the main objective is to ship models into production... - [Common Mistakes in the ML Development Lifecycle](https://mlopstalks.com/talks/common-mistakes-in-the-ml-development-lifecycle): Kseniia Melnikova, SoftwareOne. Kseniia Melnikova walks through an ML development process based on CRISP-DM and focuses on mistakes in planning, data processing, and experiments. She argues that teams... - [Model Performance Monitoring and Why You Need it Yesterday](https://mlopstalks.com/talks/model-performance-monitoring-and-why-you-need-it-yesterday): Amit Paka, Fiddler AI. Amit Paka explains why monitoring a deployed model requires more than tracking a few operational metrics. His experience with recommendation and propensity models at Samsung... - [CI/CD in MLOps](https://mlopstalks.com/talks/ci-cd-in-mlops): Monmayuri Ray, GitLab. Monmayuri Ray explains CI/CD for MLOps through economic, technical, and organizational examples. She describes AI as lowering the cost of machine prediction, while MLOps lowers... - [Operationalize Machine Learning at Scale with MLOps](https://mlopstalks.com/talks/operationalize-machine-learning-at-scale-with-mlops): Christopher Bergh, DataKitchen. Christopher Bergh argues that machine learning work needs a factory around it. The model is only one part of a chain that includes data providers,... - [Scaling AI in Production](https://mlopstalks.com/talks/scaling-ai-in-production): Srivatsan Srinivasan, AIEngineering. Srivatsan Srinivasan explains why machine learning production work extends far beyond model training. He estimates that the algorithm is only a small part of the... - [SGT Model Deployment Working Group May 19, 2021 Meeting](https://mlopstalks.com/talks/sgt-model-deployment-working-group-may-19-2021-meeting): . The meeting introduces the Social Good Tech model deployment working group and its focus on practical standards for enterprise MLOps. The discussion starts with a... - [MLOps: A Leader's Perspective](https://mlopstalks.com/talks/mlops-a-leaders-perspective): Stephen Galsworthy, Quby. Stephen Galsworthy describes MLOps from the perspective of a data leader who moved from hands-on data science into executive work at Quby. He says production... - [Learnings from Live Coding: An MLOps Project on Twitch](https://mlopstalks.com/talks/learnings-from-live-coding-an-mlops-project-on-twitch): Felipe Campos Penha, Cargill. Felipe Campos Penha describes how his work moved from computational physics into industry data science and then toward operational machine learning practices. In academia, model... - [Law of Diminishing Returns for Running AI Proof-of-Concepts](https://mlopstalks.com/talks/law-of-diminishing-returns-for-running-ai-proof-of-concepts): Oguzhan Gencoglu, Top Data Science. Oguzhan Gencoglu argues that companies often get trapped in repeated AI proof-of-concepts. A PoC that fails because the model is inaccurate has still done its... - [Organisational Challenges of MLOps](https://mlopstalks.com/talks/organisational-challenges-of-mlops): Adam Sroka, Origami Energy. Adam Sroka discusses the organisational problems behind unsuccessful machine learning projects. He describes how inexperienced data scientists can resist management, choose solutions before understanding the... - [From Idea to Production ML](https://mlopstalks.com/talks/from-idea-to-production-ml): Lex Beattie, Spotify. The discussion follows an ML project from its initial idea through deployment and monitoring. Lex Beattie says teams often choose a model before they have... - [MLOps Memes](https://mlopstalks.com/talks/mlops-memes): Ariel Biller, ClearML. Ariel Biller explains how a background in quantum chemistry, distributed computing, deep learning, and startup data science led him to evangelism at ClearML. He began... - [Luigi in Production Part 2](https://mlopstalks.com/talks/luigi-in-production-part-2): Luigi Patruno, 2U. Luigi Patruno discusses his move from individual contributor work into management at 2U. He now manages five people and oversees machine learning projects while remaining... - [War Stories Productionising ML](https://mlopstalks.com/talks/war-stories-productionising-ml): Nick Masca, Marks and Spencer. Nick Masca discusses the organisational and technical problems he has encountered while putting machine learning into production. At Marks and Spencer, he is helping bring... - [Deploying Machine Learning Models at Scale in Cloud](https://mlopstalks.com/talks/deploying-machine-learning-models-at-scale-in-cloud): Vishnu Prathish, Innovyze. Vishnu Prathish describes the MLOps platform Innovyze built for digital twins of water infrastructure. Each customer has different assets, sensor quality, and operating conditions, so... - [Machine Learning at Atlassian](https://mlopstalks.com/talks/machine-learning-at-atlassian): Geoff Sims, Atlassian. Geoff Sims describes Atlassian's move from scattered analytics work to product machine learning. When he joined, Atlassian did not depend on ML to sell its... - [MLOps Community 1 Year Anniversary!](https://mlopstalks.com/talks/mlops-community-1-year-anniversary): Demetrios B., MLOps Community & David A. & Vishnu R., Tesseract Health. The anniversary discussion turns lessons from a year of MLOps Community conversations into practical advice. David A. and Vishnu R. describe MLOps as a field... - [MLOps Investments](https://mlopstalks.com/talks/mlops-investments): Sarah Catanzaro, Amplify Partners. Sarah Catanzaro describes how her experience leading data teams shaped her work as a partner at Amplify Partners. She discusses the operational pain she saw... - [Model Watching: Keeping Your Project in Production](https://mlopstalks.com/talks/model-watching-keeping-your-project-in-production): Ben Wilson, Databricks. Ben Wilson argues that production machine learning is mainly a communication and maintenance problem. Teams need to build models with the people who understand the... - [A Missing Link in the ML Infrastructure Stack](https://mlopstalks.com/talks/a-missing-link-in-the-ml-infrastructure-stack): Josh Tobin, Stealth-Stage Startup. Josh Tobin explains why production machine learning is harder than training a model and reporting an offline score. Models face shifting data, long-tail cases, delayed... - [The Godfather Of MLOps](https://mlopstalks.com/talks/the-godfather-of-mlops): D. Sculley, Google. D. Sculley reflects on how machine learning operations has changed since his papers on technical debt and the ML Test Score. The field now has... - [Operationalizing Machine Learning at a Large Financial Institution](https://mlopstalks.com/talks/operationalizing-machine-learning-at-a-large-financial-institution): Daniel Stahl, Regions Bank. Daniel Stahl describes how Regions Bank built an on-premise machine learning platform for a regulated financial institution. The platform runs on a Hadoop data lake,... - [How to Avoid Suffering in MLOps/Data Engineering Role](https://mlopstalks.com/talks/how-to-avoid-suffering-in-mlops-data-engineering-role): Igor Lushchyk, Adyen. Igor Lushchyk talks about the habits that have helped him avoid avoidable pain in data engineering and MLOps. He recommends learning systems from small components,... - [Product Management in Machine Learning](https://mlopstalks.com/talks/product-management-in-machine-learning): Laszlo Sragner, Hypergolic. Laszlo Sragner describes how quant finance and software engineering shaped the way his team built machine learning at a fintech startup. He contrasts the usual... - [MLOps Engineering Labs Recap, Part 2](https://mlopstalks.com/talks/mlops-engineering-labs-recap-part-2): Laszlo Sranger & Artem Yushkovsky, Neuro & Paulo Maia, Nilgai. Team 3 describes how it built and deployed an NLP application during the MLOps Engineering Labs. The project uses the Yelp polarity review dataset, a... - [How Explainable AI is Critical to Building Responsible AI](https://mlopstalks.com/talks/how-explainable-ai-is-critical-to-building-responsible-ai): Krishna Gade, Fiddler AI. Krishna Gade explains why machine learning models create an operational problem that ordinary software does not. Models are black boxes whose behavior can change with... - [MLOps Engineering Labs Recap, Part 1](https://mlopstalks.com/talks/mlops-engineering-labs-recap-part-1): John Savage, Overstock & Alexey Naiden & Varuna Jayasiri & Michel Vasconcelos, Bank of Nordeste. Demetrios Brinkmann speaks with Team 1 from the first MLOps Engineering Labs. The open-ended project required MLflow and PyTorch, leaving the team to choose a... - ['Git for Data' - Who, What, How and Why?](https://mlopstalks.com/talks/git-for-data-who-what-how-and-why): Luke Feeney & Gavin Mendel-Gleason, TerminusDB. Luke Feeney surveys the open-source Git for data ecosystem and groups tools into versioning layers, data catalogs, data pipeline versioning, and version-controlled databases. He argues... - [Agile AI Ethics: Balancing Short Term Value with Long Term Ethical Outcomes](https://mlopstalks.com/talks/agile-ai-ethics-balancing-short-term-value-with-long-term-ethical-outcomes): Pamela Jasper, Jasper Consulting Inc. Pamela Jasper explains how machine learning teams can add ethical work without treating it as a separate stage that arrives after development. She proposes adding... - [Culture and Architecture in MLOps](https://mlopstalks.com/talks/culture-and-architecture-in-mlops): Jet Basrawi, Satalia. Jet Basrawi frames MLOps as a cultural and organizational problem before it is a tooling problem. He sees MLOps and DevOps as versions of the... - [2 tools = 90% operational ML](https://mlopstalks.com/talks/2-tools-90-operational-ml): Michael Del Balso, Tecton & Willem Pienaar, Feast & David Aronchick, Kubeflow. The panel discusses why operational ML needs infrastructure for both models and data. David Aronchick describes Kubeflow as a Kubernetes-native deployment and pipeline system that... - [Machine Learning Design Patterns for MLOps](https://mlopstalks.com/talks/machine-learning-design-patterns-for-mlops): Valliappa Lakshmanan, Google Cloud. Valliappa Lakshmanan explains why machine learning needs its own catalog of design patterns. The patterns come from repeated problems seen while working with customers, Google... - [Lessons Learned From Hosting the ML Engineered Podcast](https://mlopstalks.com/talks/lessons-learned-from-hosting-the-ml-engineered-podcast): Charlie You, Workday. Charlie You explains how sports betting led him from scraping public statistics to building a neural network in high school, then into machine learning engineering... - [Practical MLOps](https://mlopstalks.com/talks/practical-mlops): Noah Gift, Pragmatic AI Labs. Noah Gift argues that practical MLOps starts with treating a model like a component of a software product. Students should first take an existing model,... - [Private data, Data Science friendly](https://mlopstalks.com/talks/private-data-data-science-friendly): Jean-François Rajotte, University of British Columbia & Sumit Mukherjee, Microsoft AI for Good Research Lab. Fabiana, Jean-François Rajotte, and Sumit Mukherjee discuss synthetic data for healthcare and other settings where real data cannot be shared. Rajotte describes the practical barriers... - [Machine Learning Feature Store Panel Discussion](https://mlopstalks.com/talks/machine-learning-feature-store-panel-discussion): Vishnu Rachakonda, Tesseract Health & Daniel Galinkin, iFood & Matias Dominguez, Rappi & Simarpal Khaira, Intuit. This panel examines when teams need a feature store and how they should approach building or buying one. Matias Dominguez describes Rappi's move from a... - [ProductizeML: Assisting Your Team to Better Build ML Products](https://mlopstalks.com/talks/productizeml-assisting-your-team-to-better-build-ml-products): Adrià Romero, ProductizeML. Adrià Romero explains why he created ProductizeML after working on a healthcare application that classified skin lesions from smartphone photographs. At the startup, data scientists,... - [The revolution of Federated Learning](https://mlopstalks.com/talks/the-revolution-of-federated-learning): Fabiana Clemente, MLOps Community & Ramen Dutta, TensoAI. Ramen Dutta explains federated learning through his work with greenhouse operators and TensoAI. The approach sends models to the location of the data instead of... - [Most Underrated MLOps Topics](https://mlopstalks.com/talks/most-underrated-mlops-topics): Marian Ignev, CloudStrap.io & SashiDo.io. Marian Ignev discusses the parts of MLOps that receive too little attention. He starts with team structure. Data scientists understand algorithms, statistics, and neural network... - [Real-time Feature Pipelines, A Personal History](https://mlopstalks.com/talks/real-time-feature-pipelines-a-personal-history): Hendrik Brackmann, Tide. Hendrik Brackmann describes how his approach to machine learning production systems changed across three jobs. His first credit-risk system trained models in R and manually... - [Machine Learning Design Patterns](https://mlopstalks.com/talks/machine-learning-design-patterns): Sara Robinson, Google. Sara Robinson discusses her path from a nontraditional entry into software development to machine learning advocacy at Google. She explains why machine learning differs from... - [SRE for ML Infra](https://mlopstalks.com/talks/sre-for-ml-infra): Todd Underwood, Google. Todd Underwood argues that machine learning infrastructure is still at an early stage. The industry has developed advanced algorithms faster than it has packaged them... - [How To Move From Barely Doing BI to Doing AI](https://mlopstalks.com/talks/how-to-move-from-barely-doing-bi-to-doing-ai): Joe Reis, Ternary Data. Joe Reis argues that machine learning usually fails because companies have not solved the data and organizational problems required for ordinary business intelligence. Teams may... - [Deep in the Heart of Data](https://mlopstalks.com/talks/deep-in-the-heart-of-data): Carl Steinbach, LinkedIn. Carl Steinbach describes a career spent making Hadoop and Spark analytics feel more like databases. He explains LinkedIn's Dolly work, which decouples business logic from... - [ML and Encryption: It's All About Secure Insights](https://mlopstalks.com/talks/ml-and-encryption-its-all-about-secure-insights): Fabiana Clemente, MLOps Community & Théo Ryffel, Arkhn and Open-Mined. Théo Ryffel explains how encrypted computation can support machine learning when data or models cannot be exposed. He uses secure multiparty computation to show how... - [Privacy-preserving ML with Differential Privacy](https://mlopstalks.com/talks/privacy-preserving-ml-with-differential-privacy): Christos Dimitrakakis, University of Oslo & Fabiana Clemente. Christos Dimitrakakis explains differential privacy through randomized response, where people add a private coin toss to sensitive answers and analysts recover an aggregate estimate without... - [Human-centric ML Infrastructure: A Netflix Original](https://mlopstalks.com/talks/human-centric-ml-infrastructure-a-netflix-original): Savin Goyal, Netflix. Savin Goyal explains why Netflix built Metaflow for data scientists working across content analysis, fraud detection, recommendation systems, and other machine learning problems. The framework... - [A Conversation with Seattle Data Guy](https://mlopstalks.com/talks/a-conversation-with-seattle-data-guy): Benjamin Rogojan, Seattle Data Guy. Benjamin Rogojan discusses the gap between building a data science project and putting it into use. Early in his career, he could write an R... - [Monzo Bank - An MLOps Case Study](https://mlopstalks.com/talks/monzo-bank-an-mlops-case-study): Neal Lathia, Monzo Bank. Neal Lathia describes how Monzo uses machine learning across customer service, fraud detection, credit scoring, and features in its banking app. The team starts with... - [The intersection between DataOps and privacy](https://mlopstalks.com/talks/the-intersection-between-dataops-and-privacy): Lars Albertsson, Scling. Lars Albertsson explains DataOps as a way of working across data engineering, data science, development, and operations. He traces its roots through waterfall, agile, DevOps,... - [Are Privacy-Enhancing Technologies a Myth?](https://mlopstalks.com/talks/are-privacy-enhancing-technologies-a-myth): Fabiana Clement, MLOps Community & Charles Radcliffe. Fabiana Clement introduces privacy-enhancing technologies as methods for using data in machine learning while reducing privacy and security risks. She explains four approaches. Homomorphic encryption... - [Introducing Data Downtime: From Firefighting to Winning](https://mlopstalks.com/talks/introducing-data-downtime-from-firefighting-to-winning): Barr Moses, Monte Carlo. Barr Moses explains how her work in the Israeli Air Force, consulting, and Gainsight led her to Monte Carlo. At Gainsight, she saw that giving... - [The Current MLOps Landscape](https://mlopstalks.com/talks/the-current-mlops-landscape): Nathan Benaich, Air Street Capital & Timothy Chen, Essence VC. Nathan Benaich and Timothy Chen discuss the MLOps market from the perspective of early-stage investors. Benaich groups the market along the machine learning value chain... - [UN Global Platform](https://mlopstalks.com/talks/un-global-platform): Mark Craddock, Global Certification and Training Ltd (GCATI). Mark Craddock describes the United Nations Global Platform, which supported statistical offices in using big data alongside traditional statistics, administrative sources, and geospatial information. The... - [What are regulations saying about data privacy?](https://mlopstalks.com/talks/what-are-regulations-saying-about-data-privacy): Cat Coode. Cat Coode explains data privacy through her background in engineering, security, and privacy law. She distinguishes security, which protects systems from unauthorized access, from privacy,... - [Metaflow: Supercharging Our Data Scientist Productivity](https://mlopstalks.com/talks/metaflow-supercharging-our-data-scientist-productivity): Ravi Kiran Chirravuri, Netflix. Ravi Kiran Chirravuri explains why Netflix built Metaflow after observing data scientists work through the full machine learning project lifecycle. A useful framework has to... - [Luigi in Production](https://mlopstalks.com/talks/luigi-in-production): Luigi Patruno, ML in Production. Luigi Patruno explains why he started ML in Production, first as a newsletter and later as a blog and course project. His focus came from... - [When Machine Learning Meets Privacy, Episode 1](https://mlopstalks.com/talks/when-machine-learning-meets-privacy-episode-1): Fabiana Clemente, YData. Fabiana Clemente introduces a podcast series about data privacy in machine learning. She explains privacy as an individual's control over personal information and discusses GDPR,... - [CI/CD & Continuous Training in ML](https://mlopstalks.com/talks/ci-cd-continuous-training-in-ml): David Hershey, Determined AI. Demetrios Brinkmann and David Hershey discuss the highest automation level in Google's MLOps maturity model. At this level, teams deploy an entire pipeline rather than... - [Operationalize Open Source Models with SAS Open Model Manager](https://mlopstalks.com/talks/operationalize-open-source-models-with-sas-open-model-manager): Ivan Nardini, SAS. Ivan Nardini explains why open source models are easy to build but harder to run as business products. Business users care about the value visible... - [Data Engineering + ML + Software Engineering](https://mlopstalks.com/talks/data-engineering-ml-software-engineering): Satish Chandra Gupta, Slang Labs. Satish Chandra Gupta explains machine learning from a software engineering and data infrastructure perspective. He separates the pipeline into collection, injection, preparation, computation, and presentation,... - [Scalable Python for Everyone, Everywhere](https://mlopstalks.com/talks/scalable-python-for-everyone-everywhere): Matthew Rocklin, Coiled Computing. Matthew Rocklin presents Dask as a way to scale the existing Python data science ecosystem without replacing its familiar APIs. He demonstrates Dask Array on... - [MLOps + Machine Learning](https://mlopstalks.com/talks/mlops-machine-learning): James Sutton, Algorithmia. James Sutton discusses the engineering problems that appear when machine learning systems move from experiments into production. He explains how large embedding models can make... - [How to Choose the Right ML Tool](https://mlopstalks.com/talks/how-to-choose-the-right-ml-tool): Jose Navarro, Cookpad & Mariya Davydova, Neu.ro. Jose Navarro and Mariya Davydova discuss how ML teams should choose tools when managed services and open-source projects offer overlapping functionality. Jose recommends first checking... - [MLOps Coffee Sessions #14 Conversation with the Creators of Dask](https://mlopstalks.com/talks/mlops-coffee-sessions-14-conversation-with-the-creators-of-dask): Hugo Bowne & Matthew Rocklin, Coiled. Matthew Rocklin and Hugo Bowne explain why Dask was created and how Coiled grew around it. Rocklin describes Dask's original goal, parallel versions of NumPy,... - [MLOps #37 When You Say Data Scientist Do You Mean Data Engineer? Lessons Learned From Startup Life](https://mlopstalks.com/talks/mlops-37-when-you-say-data-scientist-do-you-mean-data-engineer-lessons-learned): Elizabeth Chabot, Deloitte. Elizabeth Chabot draws on startup and consulting work to explain why data products often fail before the model is the real problem. Companies frequently hire... - [Journey of Flyte at Lyft and Through Open-source](https://mlopstalks.com/talks/journey-of-flyte-at-lyft-and-through-open-source): Ketan Umare, Lyft. Ketan Umare explains how Flyte developed inside Lyft from an effort to automate ETA model pipelines into a general workflow and infrastructure orchestration system. Lyft... - [Analyzing "Continuous Delivery and Automation Pipelines in ML", Part 3](https://mlopstalks.com/talks/analyzing-continuous-delivery-and-automation-pipelines-in-ml-part-3): David Ponte, Benevolent AI. Demetrios Brinkmann and David Ponte use the Google paper to explain the steps from raw data to a monitored prediction service. They stress that machine... - [Moving Deep Learning from Research to Prod Using DeterminedAI & Kubeflow](https://mlopstalks.com/talks/moving-deep-learning-from-research-to-prod-using-determinedai-kubeflow): David Hershey, Determined AI. David Hershey explains how Determined AI and Kubeflow can connect research work to production workflows. Determined focuses on training rather than data management or model... - [Bring Your On-Prem ML Use Cases to Production on Google Cloud using Kubeflow](https://mlopstalks.com/talks/bring-your-on-prem-ml-use-cases-to-production-on-google-cloud-using-kubeflow): Chanchal Chatterjee, Google. Chanchal Chatterjee presents ML Pipeline Generator, an open-source project created from Google customer engagements. One retail customer had a churn model that took a team... - [Continuous Delivery and Automation Pipelines in ML, Part 2](https://mlopstalks.com/talks/continuous-delivery-and-automation-pipelines-in-ml-part-2): . David and Demetrios Brinkmann continue their discussion of Google's MLOps paper, focusing on continuous training and the pipeline around it. They explain that retraining can... - [Streaming Machine Learning with Apache Kafka and Tiered Storage](https://mlopstalks.com/talks/streaming-machine-learning-with-apache-kafka-and-tiered-storage): Kai Waehner, Confluent. Kai Waehner explains why Apache Kafka is more than a messaging system. Kafka stores ordered, timestamped events, lets producers and consumers operate independently, and supports... - [Continuous Delivery and Automation Pipelines in Machine Learning, Part 1](https://mlopstalks.com/talks/continuous-delivery-and-automation-pipelines-in-machine-learning-part-1): . Demetrios Brinkmann and David Aponte discuss Google's article on continuous delivery and automation pipelines for machine learning. They explain Google's view of MLOps as both... - [Building Say Less: An AI-Powered Summarization App](https://mlopstalks.com/talks/building-say-less-an-ai-powered-summarization-app): Yoav Zimmerman, Model Zoo. Yoav Zimmerman walks through Say Less, a tool that shortens long emails. He starts with the product idea, explains extractive and abstractive summarization, and describes... - [MLOps from the Perspective of an SRE](https://mlopstalks.com/talks/mlops-from-the-perspective-of-an-sre): Neeran Gul, Benevolent AI. Neeran Gul describes SRE work from his experience managing the SRE team at Benevolent AI. The team supports research workloads by keeping infrastructure available, reducing... - [MLOps and DevOps, Parallels and Deviations](https://mlopstalks.com/talks/mlops-and-devops-parallels-and-deviations): Damian Brady, Microsoft. Damian Brady describes MLOps as closely related to DevOps at the level of purpose. Both aim to move a solution from an idea into production... - [Creating Beautiful Ambient Music with Google Brain's Music Transformer](https://mlopstalks.com/talks/creating-beautiful-ambient-music-with-google-brains-music-transformer): Daniel Jeffries, Pachyderm. Daniel Jeffries explains why he chose ambient music as a practical machine learning project instead of a small tutorial dataset. He trained Google Brain's Magenta... - [Path to Production and Monetizing Machine Learning](https://mlopstalks.com/talks/path-to-production-and-monetizing-machine-learning): Vin Vashishta. Vin Vashishta argues that companies cannot expect machine learning profits to appear after hiring data scientists. Teams need a repeatable process that connects business problems... - [MLOps Cubonacci workshop](https://mlopstalks.com/talks/mlops-cubonacci-workshop): . Jan presents machine learning operations through three problems: deployment, reproducibility, and automation. Deployment turns a trained model into a request-based, batch, or streaming service that... - [Scaling ML Capabilities in Large Organizations](https://mlopstalks.com/talks/scaling-ml-capabilities-in-large-organizations): Bertjan Broeksema & Axel Goblet, BigData Republic. Bertjan Broeksema and Axel Goblet describe how companies move from isolated machine learning proofs of concept to systems that deliver value in production. Each successful... - [Continuous Integration for ML](https://mlopstalks.com/talks/continuous-integration-for-ml): Elle O'Brien, Iterative. Elle O'Brien describes her move from academic research in computational neuroscience to data science at Iterative. She found a large gap between research coding, which... - [Airflow in MLOps](https://mlopstalks.com/talks/airflow-in-mlops): Simon Darr & Byron Allen, Servian. Simon Darr and Byron Allen explain where Airflow fits in data engineering and MLOps. Darr describes it as a batch ETL scheduler and says Airflow... - [Introducing MLOps Engineering Labs - Join us to better your skills](https://mlopstalks.com/talks/introducing-mlops-engineering-labs-join-us-to-better-your-skills): . David Aponte and Ivan introduce Engineering Labs, an initiative from MLOps Community for practicing the engineering work around machine learning systems. The labs are intended... - [A Conversation Around Feature Stores](https://mlopstalks.com/talks/a-conversation-around-feature-stores): Venkata Pingali, Scribble Data. Jim Dowling and Venkata Pingali explain why feature stores emerged as machine learning teams grew beyond ad hoc feature engineering. Jim describes a feature store... - [Continuous Evaluation & Model Experimentation](https://mlopstalks.com/talks/continuous-evaluation-model-experimentation): Danny Ma, Sydney Data Science. Danny Ma explains experimentation from the parts of machine learning that happen before model serving. He covers hyperparameter search, algorithm comparison, feature engineering, and changes... - [ML Observability](https://mlopstalks.com/talks/ml-observability): Aparna Dhinakaran, Arize AI. Aparna Dhinakaran explains why deployed machine learning models need different monitoring from ordinary software. Model behavior depends on incoming data, which can change in ways... - [How to Leverage ML Tooling Ecosystem](https://mlopstalks.com/talks/how-to-leverage-ml-tooling-ecosystem): Mariya Davydova, Neu.ro. Mariya Davydova walks through Neu.ro's workflow for developing and operating an object-recognition system for retail. New images arrive from shops, so the model needs frequent... - [MLOps: Isn't That Just DevOps?](https://mlopstalks.com/talks/mlops-isnt-that-just-devops): Ryan Dawson, Seldon. Ryan Dawson explains why MLOps overlaps with DevOps but cannot be reduced to it. Traditional software starts with code and produces an executable or web... - [Python and Dask: Scaling the DataFrame](https://mlopstalks.com/talks/python-and-dask-scaling-the-dataframe): Dan Gerlanc, Enplus Advisors. Dan Gerlanc gives a practical introduction to Dask DataFrames. He explains how Dask keeps the pandas mental model while splitting a logical DataFrame into smaller... - [Feature Stores: An Essential Part of the ML Stack to Build Great Data](https://mlopstalks.com/talks/feature-stores-an-essential-part-of-the-ml-stack-to-build-great-data): Kevin Stumpf, Tecton. Kevin Stumpf explains why production ML needs infrastructure for data as well as infrastructure for models. Features are curated values derived from raw data, such... - [How to Become a Better Data Scientist: The Definitive Guide](https://mlopstalks.com/talks/how-to-become-a-better-data-scientist-the-definitive-guide): Alexey Grigorev, OLX Group. Alexey Grigorev describes a full-stack data scientist as someone who can own a machine learning project from requirements gathering to deployment. This does not mean... - [Monitoring the Machine Learning Stack](https://mlopstalks.com/talks/monitoring-the-machine-learning-stack): Lina Weichbrodt, DKB. Lina Weichbrodt explains why standard software monitoring misses serious machine learning failures. A request can be fast and error-free while returning empty recommendations, the wrong... - [Deep Dive on Paperspace Tooling](https://mlopstalks.com/talks/deep-dive-on-paperspace-tooling): Misha Kutsovsky, Paperspace. Misha Kutsovsky describes how Paperspace expanded from GPU-backed virtual machines into Gradient, a platform for developing, scaling, and deploying machine learning systems. The product combines... - [Different Ways of Serving ML Models](https://mlopstalks.com/talks/different-ways-of-serving-ml-models): Byron Allen. Demetrios Brinkmann, David Aponte, and Byron Allen discuss three patterns from Bugra Akyildiz's blog post: offline prediction materialized in a database, an embedded model inside... - [Build vs Buy an ML Platform](https://mlopstalks.com/talks/build-vs-buy-an-ml-platform): Diego Oppenheimer, Algorithmia. Diego Oppenheimer explains why an ML platform is much more than a model-serving API. A team must support serialized models, model and source-code versioning, reusable... - [DataOps and Data Versioning in ML](https://mlopstalks.com/talks/dataops-and-data-versioning-in-ml): Dmitry Petrov, Iterative.AI. Dmitry Petrov explains why machine learning needs a versioning system for data alongside code versioning. Datasets can be too large for traditional systems, and teams... - [Running a Fintech on Machine Learning](https://mlopstalks.com/talks/running-a-fintech-on-machine-learning): Caique Lima & Cristiano Breuel, Nubank. Caique Lima and Cristiano Breuel describe how Nubank runs machine learning inside a technology-led financial services company. Machine learning supports credit decisions, fraud detection, and... - [Serving Models with Kubeflow](https://mlopstalks.com/talks/serving-models-with-kubeflow): . David Aponte and Demetrios Brinkmann use their first MLOps Coffee Session to explain model serving through Kubeflow. David defines serving as making predictions from a... - [MLflow Open Source Framework Hermione Demo](https://mlopstalks.com/talks/mlflow-open-source-framework-hermione-demo): Neylson Crepalde, A3Data. Neylson Crepalde demonstrates Hermione, an open-source machine learning project framework built on top of MLflow. The demo starts by installing Hermione with Conda and creating... - [The Challenges of ML Operations & How Hermione Helps Along the Way](https://mlopstalks.com/talks/the-challenges-of-ml-operations-how-hermione-helps-along-the-way): Neylson Crepalde, A3Data. Neylson Crepalde describes the problems A3Data saw when moving machine learning work from an individual or academic setting into professional teams. Different Python versions, libraries,... - [What is the open source ML framework Hermoine](https://mlopstalks.com/talks/what-is-the-open-source-ml-framework-hermoine): Neylson Crepalde, A3Data. Neylson Crepalde presents Hermoine, an open-source ML project structure framework built on top of MLflow. He starts with the gap between casual data science work... - [Venture Capital in Machine Learning Startups](https://mlopstalks.com/talks/venture-capital-in-machine-learning-startups): John Spindler, Capital Enterprise. John Spindler explains how he evaluates machine learning startups as an investor at Capital Enterprise and AI Seed. He compares machine learning deals with ordinary... - [Scaling Human-in-the-Loop Machine Learning](https://mlopstalks.com/talks/scaling-human-in-the-loop-machine-learning): Robert Munro. Robert Munro explains that human-in-the-loop machine learning is already common because supervised systems improve with additional human data. The hard work includes choosing what to... - [Kubeflow vs MLflow](https://mlopstalks.com/talks/kubeflow-vs-mlflow): Byron Allen, Servian. Byron Allen explains why comparing MLflow and Kubeflow directly can mislead. MLflow is a lightweight package that practitioners can install locally or on a virtual... - [Maximizing Job Opportunities as a Data Scientist on the Market](https://mlopstalks.com/talks/maximizing-job-opportunities-as-a-data-scientist-on-the-market): Anthony Kelly, AI in Action. Anthony Kelly explains how data scientists and machine learning engineers can get more opportunities from the same job search. He recommends tailoring resumes to the... - [Why Data Scientists Should Know Data Engineering](https://mlopstalks.com/talks/why-data-scientists-should-know-data-engineering): Dan Sullivan. Dan Sullivan explains why data scientists benefit from learning data engineering. Data engineering adds the skills needed to move, clean, scale, and process data when... - [Fury Platform and Fury Data Apps at Mercado Libre](https://mlopstalks.com/talks/fury-platform-and-fury-data-apps-at-mercado-libre): Carlos de la Torre, Mercado Libre. Carlos de la Torre describes how Mercado Libre's machine learning work grew from separate fraud detection and recommendation projects into a platform effort. Different teams... - [Machine Learning at Scale in Mercado Libre](https://mlopstalks.com/talks/machine-learning-at-scale-in-mercado-libre): Carlos de la Torre, Mercado Libre. Carlos de la Torre explains how Mercado Libre extended its Fury platform to support machine-learning work across the company. Before Fury Data Apps, teams used... - [10 Years Deploying ML in the Enterprise: The Inside Scoop!](https://mlopstalks.com/talks/10-years-deploying-ml-in-the-enterprise-the-inside-scoop): Charles Martin, MLOps Community. Charles Martin argues that enterprise ML projects often fail because organizations force new machine learning workflows into deployment systems built for older web applications. A... - [MLOps - The Blind Men and the Elephant](https://mlopstalks.com/talks/mlops-the-blind-men-and-the-elephant): Saurav Chakravorty, Brillo. Saurav Chakravorty explains MLOps through the story of blind men describing an elephant. Business analysts want fast answers and may accept lower reproducibility. Software engineers... - [Optimizing Your ML Workflow with Kubeflow 1.0](https://mlopstalks.com/talks/optimizing-your-ml-workflow-with-kubeflow-1-0): Josh Bottum, Arrikto. Josh Bottum presents Kubeflow 1.0 as a composable set of tools for developing, training, deploying, and managing machine learning on Kubernetes. He argues that teams... - [TrueLayer's MLOps Pipeline](https://mlopstalks.com/talks/truelayers-mlops-pipeline): Alex Spanos, TrueLayer. Alex Spanos describes how TrueLayer introduced machine learning into its Open Banking API products. The company classifies bank transactions, identifies merchants, and adds categories and... - [High Stakes ML: Active Failures, Latent Factors](https://mlopstalks.com/talks/high-stakes-ml-active-failures-latent-factors): Flavio Clesio, MyHammer AG. Flavio Clesio argues that the era of one data scientist training a model in a single machine is over for serious machine learning systems. Regulation,... - [Mid-Scale Production Feature Engineering](https://mlopstalks.com/talks/mid-scale-production-feature-engineering): Dr. Venkata Pingali, Scribble Data. Dr. Venkata Pingali explains why feature engineering needs the same discipline applied to software systems. His concern began with marketing projects where teams optimized for... - [Building an ML Platform at SurveyMonkey](https://mlopstalks.com/talks/building-an-ml-platform-at-surveymonkey): Shubhi Jain, SurveyMonkey. Shubhi Jain explains how SurveyMonkey moved from separate microservices for each ML use case to a shared ML platform. The team first defined its requirements... - [Hierarchy of Machine Learning Needs](https://mlopstalks.com/talks/hierarchy-of-machine-learning-needs): Phil Winder, Winder Research. Phil Winder argues that MLOps needs to include the software and organizational foundations underneath machine learning. Practices such as continuous training, provenance, and reproducibility have... - [What Does Best in Class AI/ML Governance Look Like in Fin Services?](https://mlopstalks.com/talks/what-does-best-in-class-ai-ml-governance-look-like-in-fin-services): Charles Radclyffe, Technology Governance and ESG Specialist, AI Ethics. Charles Radclyffe describes his experience leading AI at Fidelity, where machine learning projects had grown through side-of-desk experiments, senior requests, and work without clear business... - [Our 1st MLOps Meetup](https://mlopstalks.com/talks/our-1st-mlops-meetup): Luke Marsden, Dotscience. Luke Marsden introduces MLOps as the intersection of software engineering, DevOps, and machine learning. He describes machine learning teams that can train models on laptops... ## Index pages - [Talks from 2026](https://mlopstalks.com/talks/2026): 100 talks - [Talks from 2025](https://mlopstalks.com/talks/2025): 170 talks - [Talks from 2024](https://mlopstalks.com/talks/2024): 207 talks - [Talks from 2023](https://mlopstalks.com/talks/2023): 174 talks - [Talks from 2022](https://mlopstalks.com/talks/2022): 99 talks - [Talks from 2021](https://mlopstalks.com/talks/2021): 99 talks - [Talks from 2020](https://mlopstalks.com/talks/2020): 78 talks - [All packs](https://mlopstalks.com/packs) - [By series](https://mlopstalks.com/series) - [By speaker](https://mlopstalks.com/speakers) - [By company](https://mlopstalks.com/companies) - [By topic](https://mlopstalks.com/tags) - [RSS feed](https://mlopstalks.com/rss.xml)