Staff AI Retrieval Engineer — Grounded Agent Context

Perot Jain; Minneapolis (MN); Hybrid; USD 170,000 - 297,000; Full time

Benefits offered by this job

Health insurance

Retirement plan

Paid time off to employees

Job summary

Datasite is hiring a Staff Software Engineer to own the context AI agents used in live M&A deals. You will develop the retrieval layer to ground agent answers in the right documents while ensuring security and permissioning.

You will work in Python and partner with Product and Data Science, staying hands-on on decisions that affect what an agent can know. You will join a hybrid team with offices in New York City and Minneapolis, collaborating with product and data science to evolve the agent

Qualifications

• 6+ years of building and operating production software.
• Strong hands-on Python with backend services and APIs.
• Experience with production LLM applications that depend on retrieval: tool calling, RAG, embeddings, vector search, or context management.

Responsibilities

• Own retrieval for agents that work on live deals and ground answers in documents and data.
• Scale platform to process large documents and data tables.
• Shape the context agents rely on as deal workflows grow more complex.
• Build search tools for indexed and non-indexed content, returning snippets and citations.
• Ensure agent context aligns with data rooms and access permissions.
• Decide when models may answer from retrieved context vs. product checks.
• Mentor engineers and set technical direction for retrieval across teams.

Skills

Python

Backend APIs

Data pipelines

LLM retrieval

Vector search

Permissions & multi-tenant data

Product & technical judgment

Tools

Vector store

Embeddings

Job description

Datasite is hiring a Staff Software Engineer to own the context AI agents used in live M&A deals. You will develop the retrieval layer to ground agent answers in the right documents while ensuring security and permissioning.

You will work in Python and partner with Product and Data Science, staying hands-on on decisions that affect what an agent can know. You will join a hybrid team with offices in New York City and Minneapolis, collaborating with product and data science to evolve the agent