Manage episode 524556966 series 3241972
Simba Khadder is the founder and CEO of Featureform, now at Redis, working on real-time feature orchestration and building a context engine for AI and agents.
Context Engineering 2.0, Simba Khadder // MLOps Podcast #352
Join the Community:
https://go.mlops.community/YTJoinIn
Get the newsletter: https://go.mlops.community/YTNewsletter
// Abstract
Feature stores aren’t dead — they were just misunderstood. Simba Khadder argues the real bottleneck in agents isn’t models, it’s context, and why Redis is quietly turning into an AI data platform. Context engineering matters more than clever prompt hacks.
// Bio
Simba Khadder is the founder and CEO of Featureform, the virtual feature store that empowers data scientists to define, manage, and serve model features using a Python framework. He began his machine learning career in recommender systems, where he architected a multi-modal personalization engine that enhanced the experiences of hundreds of millions of users. Later, he open-sourced the data platform that powered this model and built a company around it, Featureform. Outside of ML, Simba is a published astrophysicist, an avid surfer, and once ran a marathon in basketball shoes.
// Related Links
Website: featureform.comhttps://marketing.redis.io/blog/real-time-structured-data-for-ai-agents-featureform-is-joining-redis/
~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~
Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore
Join 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: /dpbrinkm
Connect with Simba on LinkedIn: /simba-k/
Timestamps:
[00:00] Context engineering explanation
[00:25] MLOps and feature stores
[03:36] Selling a company experience
[06:34] Redis feature store evolution
[12:42] Embedding hub
[20:42] Human vs agent semantics
[26:41] Enrich MCP data flow
[29:55] Data understanding and embeddings
[35:18] Search and context tools
[39:45] MCP explained without hype
[45:15] Wrap up
489 episodes