AI Context & Data Infrastructure Engineer

Town.com, Inc.; San Francisco (CA); Vor Ort; USD 180.000 - 280.000; Vollzeit

Zusammenfassung

Town.com, Inc. is shaping the next generation of AI assistants by personalizing context across every tool.

You will build the foundational search and data retrieval layer, a shared platform that unifies lexical and semantic search, while balancing latency, cost, and accuracy at scale. You will design durable data models and oversee realtime/streaming and batch pipelines, ensuring fresh and correct indexing.

Qualifikationen

• Hands-on experience with lexical and semantic search components and approaches (BM25, embeddings, ANN/vector indexes, hybrid retrieval, ranking).
• Experience running large-scale data infrastructure, ideally both realtime/streaming and batch pipelines, indexing, and storage.
• Ability to optimize retrieval for speed and cost at scale; systems thinking in greenfield environments.

Aufgaben

• Build the search and retrieval layer that puts the right context at users' fingertips across Town's product.
• Combine lexical and semantic search and manage tradeoffs between vector vs lexical methods, precompute vs fetch, and ranking.
• Design a durable data model so context is fast, relevant, and cost-efficient.
• Build and operate real-time/streaming and batch pipelines to keep the index fresh and correct.
• Stand up the indexing and storage layer and ensure latency, cost, freshness, and completeness at scale.
• Lay groundwork for relating content by meaning across people, companies, projects, and connections.

Kenntnisse

Lexical and semantic search

BM25

Embeddings

ANN/vector indexes

Hybrid retrieval

Ranking

Large-scale data infrastructure

Real-time streaming

Batch processing

Search pipelines

Jobbeschreibung

About Town

Town (town.com) is AI that starts from who you are. We build a persistent model of your identity, your voice, your judgment, your relationships, and your priorities, and use it to do real work on your behalf across every tool where you operate: email, calendar, documents, Slack, and more. Town doesn’t wait for you to prompt it. It observes, learns, and acts. The more you use it, the more it becomes an extension of you.

Town was founded by Jean-Denis Greze (CEO), former CTO of Plaid, and Tony Vincent (CPO), former Director of Applied AI Product at Google. We’re a small, talent-dense team backed by Andreessen Horowitz, Forerunner Ventures, First Round Capital, and Conviction, with more than $73M raised to date.

About the role

Town is building the most personalized, most capable AI assistant for everyone — and personalization at that level is a retrieval and data problem. The assistant is only as good as the context it can bring into the moment: the right memory, message, document, or relationship, pulled fast and related by meaning across everything a person and their team touch.

You’ll build the foundation the whole product reasons over: the search and data infrastructure behind that context. One shared retrieval layer combining lexical and semantic search, the realtime and batch pipelines that keep it fresh and correct, and the durable data model everything else is built on.

This is greenfield and high-leverage: you’ll be the first person building this layer.

What you’ll do

• Build the search and retrieval layer that puts the right context at every Townie’s fingertips, the moment it’s needed — one shared layer the whole product pulls from instead of refetching context on its own.

• Combine lexical and semantic search and own the tradeoffs between them: vector vs. lexical, precompute vs. fetch, hybrid retrieval, and ranking.

• Design the durable data model the assistant’s work is built on, so context is relevant, fast, and cost-effective.

• Build and operate the pipelines behind it — realtime/streaming and batch — that keep the index fresh and correct as the underlying data changes.

• Stand up the indexing and storage layer and keep it fast and reliable at scale: latency, cost, freshness, and completeness.

• Lay the groundwork for relating content by meaning across everything the assistant knows — the start of a knowledge graph of people, companies, projects, and how they connect.

You might thrive here if you…

• Have significant, hands‑on experience across lexical and semantic search components and approaches (BM25, embeddings, ANN/vector indexes, hybrid retrieval, ranking).

• Have run large‑scale data infrastructure, ideally both realtime/streaming and batch — pipelines, indexing, and storage.

• Can make retrieval fast and cheap at scale, and reason about the latency, cost, and freshness tradeoffs cold.

• Are a systems thinker comfortable in greenfield, where the foundation doesn’t exist yet.

• Are excited to take these systems from rapid prototype to production scale.

• Bonus if you’ve worked on ranking/relevance, knowledge graphs, or retrieval for LLM or agentic systems.

Location

San Francisco, CA. Five days a week in person at our Financial District office.