As machine learning and generative AI continue to evolve, the demands placed on retrieval infrastructure grow exponentially. In this talk, we’ll go under the hood of vector databases to explore the real engineering challenges of scaling intelligent search. From designing storage engines optimized for high-dimensional data, to handling distributed indexing and retrieval at scale, this session will unpack the technical decisions, trade-offs, and innovations that power modern AI-native systems. Drawing on lessons from building Weaviate from the ground up, this talk offers a behind-the-scenes look at what it takes to keep up with AI’s rapid pace—while keeping performance, scalability, and developer experience front and center.