The opportunity
Anthropic is looking for a Staff+ Software Engineer to work on the vector search infrastructure behind Claude. Retrieval is how Claude learns about the world.
What you'll do
Own the core of Anthropic's vector database layer: index structures, storage layout, query execution and the serving layer
Own production readiness: benchmarking against exact search, capacity planning, onboarding new workloads, and the operational tooling to run it at scale
Drive the recall, latency and cost trade-offs: quantization, filtered search, index build and refresh strategy, and how compute and storage are separated and scaled
Scale throughput by an order of magnitude as research and training demand: grows, and work out whether the bottleneck is architecture, hardware or engineering bandwidth
Extend the retrieval stack toward hybrid retrieval: lexical search and fused ranking alongside vector search
Set the evaluation methodology for the system: recall targets, latency objectives, cost per query, and the regression detection that keeps them honest
What they're looking for
- Experience with object-storage-backed or disaggregated compute and storage database designs
- Experience building or operating full-text search engines (inverted indexes, BM25) or hybrid retrieval systems
- Familiarity with embedding models and the retrieval demands of LLM training and inference
- Experience using GPUs or other accelerators for index build or search
- Prior experience as a technical lead on a database or search infrastructure team