Discover the latest trends and best practices impacting data-intensive applications. Register for access to all 60+ sessions available on demand.
Building a trillion-scale vector search system is one challenge; running it as a multi-tenant SaaS service is another. 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 search.
Nikhil Benesch is a systems engineer at turbopuffer who specializes in full-text search. He has a strange obsession with handling data at scale. Before joining turbopuffer, he was CTO and co-founder of Materialize, a real-time SQL database.
