AI Context & Data Infrastructure Engineer

7 days ago

Base Salary

$250k - $300k/yr

Responsibilities

Build a shared search and retrieval layer that provides relevant context across Town’s products.
Combine lexical and semantic search and make tradeoffs involving vector versus lexical retrieval, precomputation versus fetching, hybrid retrieval, and ranking.
Design the durable data model supporting the assistant’s context and work.
Build and operate real-time/streaming and batch pipelines that keep indexes fresh and correct.
Stand up and scale indexing and storage infrastructure while managing latency, cost, freshness, completeness, and reliability.
Lay the groundwork for a knowledge graph connecting people, companies, projects, and relationships.

Significant hands-on experience with lexical and semantic search, including BM25, embeddings, approximate nearest neighbor/vector indexes, hybrid retrieval, and ranking.
Experience running large-scale data infrastructure across real-time/streaming and batch pipelines, indexing, and storage.
Ability to optimize retrieval for speed and cost at scale and reason about latency, cost, and freshness tradeoffs.
Systems-thinking ability and comfort building greenfield foundations from prototype to production scale.
Experience with ranking/relevance, knowledge graphs, or retrieval for LLM or agentic systems is a bonus.

Five days per week in person at Town’s Financial District office in San Francisco, California.
Opportunity to be the first engineer building a high-leverage, greenfield search and data infrastructure layer.

11-50 employees