Town
AI Context & Data Infrastructure Engineer
$250K–$300K
San Francisco · On-site · Full-time · Posted Aug 29, 2026
About the job
Build Town’s shared search and data infrastructure to retrieve fresh, relevant context for its AI assistants.
What you'll do
- Build a shared retrieval layer combining lexical and semantic search, hybrid retrieval, and ranking.
- Design durable data models and operate real-time/streaming and batch pipelines, indexing, and storage.
- Improve retrieval speed, cost, freshness, completeness, and reliability at scale; lay groundwork for a knowledge graph.
What they ask for
- Significant hands-on experience with lexical and semantic search components and approaches.
- Experience running large-scale data infrastructure, ideally including both real-time/streaming and batch systems.
- Ability to reason about latency, cost, and freshness tradeoffs in retrieval at scale.
- Comfort working in a greenfield environment and taking systems from prototype to production scale.
Nice to have
- Experience with ranking/relevance or knowledge graphs.
- Experience with retrieval for LLM or agentic systems.
Pay
$250K – $300K
Tools
BM25, embeddings, ANN/vector indexes
AI focus
Build retrieval and data infrastructure supplying relevant context to AI assistants; potential work relating content by meaning and supporting LLM or agentic retrieval.
Model-written summary · the original posting is authoritative