Staff Software Engineer - Agentic Search & Retrieval (Hybrid)

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

Benefits offered by this job

Health insurance

Retirement plan

Paid time off

Employee benefits

Job summary

Datasite is hiring a Staff Software Engineer to own the retrieval layer used by live deal AI agents. You will ground answers in documents, manage permissions, and build scalable Python services for large-scale data.

This role collaborates with Product and Data Science, shaping context for multi-tenant environments, mentoring engineers, and keeping hands-on influence on what an agent can know.

Qualifications

• 6+ years of building and operating production software.
• Strong hands-on Python, with experience in backend services, APIs, and large-scale data pipelines.
• Experience with production LLM applications that depend on retrieval: tool calling, RAG, embeddings, vector search, or context management.
• Strong foundations in permissions, multi-tenant data, and access control on what an agent can retrieve.
• Clear product and technical judgment.

Responsibilities

• Own retrieval for agents that work on live deals.
• Ground each answer in the right documents and data, and set the balance of quality, speed, and cost.
• Scale platform processing of large documents and data tables for multi-pass reasoning.
• Shape context agents depend on and evolve it as deal workflows grow.
• Build search tools, cover indexed and non-indexed content, return snippets and citations.
• Maintain agent context alignment with data rooms and access permissions.

Skills

Python

Backend services

APIs

Data pipelines

Product judgment

Tools

Vector search

Embeddings

LLM applications

Job description

Datasite is hiring a Staff Software Engineer to own the retrieval layer used by live deal AI agents. You will ground answers in documents, manage permissions, and build scalable Python services for large-scale data.

This role collaborates with Product and Data Science, shaping context for multi-tenant environments, mentoring engineers, and keeping hands-on influence on what an agent can know.