Chandrashekhar Medicherla

Title of the Talk: Teaching Databases to Tune Themselves: Adaptive Index Selection at the Edge

Abstract:
Vector databases now power everything from smart-city sensor search to industrial monitoring, but one critical decision is still made by hand: which index to use. Get it wrong, and you’re looking at sluggish queries or a gateway that crashes under load at the worst possible moment. This talk explores what it takes to let a database make that decision on its own. I’ll walk through how a lightweight machine-learning system can watch a workload in real time and switch indexing strategies automatically, and why doing this safely, without surprising the people who depend on the system, is harder and more interesting than the prediction itself. Along the way we’ll talk about treating configuration as an ongoing control problem rather than a one-time setup, and what changes when your system has to make these calls on edge hardware with no human in the loop. Attendees will leave with a fresh way of thinking about self-tuning infrastructure and where it’s headed next.

Bio:
Chandrashekhar Medicherla is Lead Software Engineer – Database Infrastructure at Salesforce Inc., where he manages enterprise-scale database systems serving millions of users worldwide. With 18+ years of expertise in database infrastructure and cloud computing, he specializes in building reliable systems that achieve 99.99% uptime while processing billions of transactions daily.

Chandrashekhar serves as Vice Chair of the Bluffdale ACM Chapter. He holds Fellow status with IETE, Senior Member status with IEEE, and Distinguished Fellow status with the Soft Computing Research Society. He has authored 16+ published research articles indexed in IEEE and Google Scholar and contributed 60+ peer reviews for IEEE and Elsevier publications. His work spans database systems, cloud architecture, and AI infrastructure across SaaS, financial services, healthcare, and internet-scale environments.