Complete gig history
All talks by Nikhil Benesch
3 talks·ongoing
Loading talks…
The playbook for building a startup hasn't changed much in 20 years - until now. Fewer people, different skills, and a completely different sense of what's possible. A new generation of founders is shipping products with smaller teams, moving faster, and using AI across every function. Join a group of AI-native founders for a candid look at how they're actually using AI inside their own companies - in their workflows, their code, their ops - and what the shape of their teams looks like as a result.
This talk goes beyond architecture diagrams to share what actually happens when you operate an agentic search engine on trillions of documents. We'll dig into how an object storage-native design allows a small team of engineers to manage an AI search engine that scales to: Peak load of 1M+ writes per second and 30k+ searches per second, 1+ trillion documents, 5+ PB of logical data, 400+ tenants, p90 query latency <100 ms. Topics include: How using a modern storage architecture decreases COGS by 10x or more, Optimizing traditional vector and FTS indexes for the high latency of object storage, Building search algorithms that are fine-tuned for LLM-initiated searches, A simple rate-limiting technique that provides strong performance isolation in multi-tenant environments, Observability, reliability, and performance lessons learned from production incidents. Attendees will leave with a concrete understanding of how separating storage from compute-and treating object storage as the primary database changes not only the cost structure, but the entire operational model of large-scale AI search.