GPU Considerations, Labeling Privacy, Rapid Fine Tuning, and the Role of Private Eval Pipelines to Benchmark New Models
Agents in Production [Podcast Limited Series] Episode Nine – Training LLMs, Picking the Right Models, and GPU HeadachesPaul van der Boor and Zulkuf Genc from Prosus join Demetrios to talk about what it really takes to get AI agents running in production. From building solid eval sets to juggling GPU logistics and figuring out which models are worth using (and when), they share hard-won lessons from the front lines. If you're working with LLMs at scale—or thinking about it—this one’s for you.Guest speakers:Paul van der Boor - VP AI at Prosus GroupZulkuf Genc - Director of AI at Prosus GroupHost:Demetrios Brinkmann - Founder of MLOps Community~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]
--------
55:46
--------
55:46
The Hidden Bottlenecks Slowing Down AI Agents
Demetrios chats with Paul van der Boor and Bruce Martens from Prosus about the real bottlenecks in AI agent development—not tools, but evaluation and feedback. They unpack when to build vs. buy, the tradeoffs of external vendors, and how internal tools like Copilot are reshaping workflows.Guest speakers:Paul van der Boor - VP AI at Prosus GroupBruce Martens - AI Engineer at Prosus GroupHost:Demetrios Brinkmann - Founder of MLOps Community~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]
--------
47:59
--------
47:59
9 Commandments for Building AI Agents
Building AI agents that actually get things done is harder than it looks. Demetrios, Paul, and Dmitri break down what makes agents effective—from smart planning and memory to treating tools, systems, and even people as components. They cover the "react" loop, budgeting for long tasks, sandboxing, and learning from experience. It’s a sharp, practical look at what it really takes to design useful, adaptive AI agents.Guest speakers:Paul van der Boor - VP AI at Prosus GroupDmitri Jarnikov - Senior Director of Data Science at Prosus GroupHost:Demetrios Brinkmann - Founder of MLOps Community~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]
--------
1:20:33
--------
1:20:33
Enterprise AI Adoption Challenges
Building AI Agents that work is no small feat.In Agents in Production [Podcast Limited Series] - Episode Six, Paul van der Boor and Sean Kenny share how they scaled AI across 100+ companies with Toqan—a tool born from a Slack experiment and grown into a powerful productivity platform. From driving adoption and building super users to envisioning AI employees of the future, this conversation cuts through the hype and gets into what it really takes to make AI work in the enterprise.Guest speakers:Paul van der Boor - VP AI at Prosus GroupSean Kenny - Senior Product Manager at Prosus GroupHost:Demetrios Brinkmann - Founder of MLOps Community~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]
--------
1:05:00
--------
1:05:00
Real-time Feature Generation at Lyft // Rakesh Kumar // #334
Real-time Feature Generation at Lyft // MLOps Podcast #334 with Rakesh Kumar, Senior Staff Software Engineer at Lyft.Join the Community: https://go.mlops.community/YTJoinInGet the newsletter: https://go.mlops.community/YTNewsletter// AbstractThis session delves into real-time feature generation at Lyft. Real-time feature generation is critical for Lyft where accurate up-to-the-minute marketplace data is paramount for optimal operational efficiency. We will explore how the infrastructure handles the immense challenge of processing tens of millions of events per minute to generate features that truly reflect current marketplace conditions. Lyft has built this massive infrastructure over time, evolving from a humble start and a naive pipeline. Through lessons learned and iterative improvements, Lyft has made several trade-offs to achieve low-latency, real-time feature delivery. MLOps plays a critical role in managing the lifecycle of these real-time feature pipelines, including monitoring and deployment. We will discuss the practicalities of building and maintaining high-throughput, low-latency real-time feature generation systems that power Lyft’s dynamic marketplace and business-critical products.// BioRakesh Kumar is a Senior Staff Software Engineer at Lyft, specializing in building and scaling Machine Learning platforms. Rakesh has expertise in MLOps, including real-time feature generation, experimentation platforms, and deploying ML models at scale. He is passionate about sharing his knowledge and fostering a culture of innovation. This is evident in his contributions to the tech community through blog posts, conference presentations, and reviewing technical publications.// Related LinksWebsite: https://englife101.io/https://eng.lyft.com/search?q=rakeshhttps://eng.lyft.com/real-time-spatial-temporal-forecasting-lyft-fa90b3f3ec24https://eng.lyft.com/evolution-of-streaming-pipelines-in-lyfts-marketplace-74295eaf1ebaStreaming Ecosystem Complexities and Cost Management // Rohit Agrawal // MLOps Podcast #302 - https://youtu.be/0axFbQwHEh8~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]Connect with Demetrios on LinkedIn: /dpbrinkmConnect with Rakesh on LinkedIn: /rakeshkumar1007/Timestamps:[00:00] Rakesh preferred coffee[00:24] Real-time machine learning[04:51] Latency tricks explanation[09:28] Real-time problem evolution[15:51] Config management complexity[18:57] Data contract implementation[23:36] Feature store[28:23] Offline vs online workflows[31:02] Decision-making in tech shifts[36:54] Cost evaluation frequency[40:48] Model feature discussion[49:09] Hot shard tricks[55:05] Pipeline feature bundling[57:38] Wrap up
Canada - english