Staff Software Engineer, Agentic Search & Retrieval
About The Position
Datasite is hiring a hands-on Staff Software Engineer to own the retrieval layer that supplies context to AI agents working on live deals. The role focuses on ensuring agent answers are grounded in the right documents and data, current, and secure, while balancing retrieval quality, speed, and cost. The engineer will work in Python and partner closely with Product and Data Science. The position is based in New York City or Minneapolis at a hybrid company, with in-office collaboration on Mondays, Tuesdays, and Thursdays. The engineer will scale processing of large documents and data tables, shape context for longer and more complex deal workflows, build agent search tools for indexed and not-yet-indexed content, and ensure returned snippets, citations, and locations are trustworthy. The role also safeguards permissions so agents only retrieve content users may access, determines when retrieved context is sufficient for a model to answer versus when results require product checks, and mentors engineers while setting technical direction for retrieval across teams.
Requirements
- At least 6 years of experience building and operating production software, with a record of leading complex technical work across teams.
- Strong hands-on Python skills and experience with backend services, APIs, and large-scale data pipelines.
- Experience with production LLM applications that depend on retrieval, such as tool calling, RAG, embeddings, vector search, or context management.
- Strong foundations in permissions, multi-tenant data, and access control for agent retrieval.
- Clear product and technical judgment, including balancing answer quality, latency, and cost and explaining tradeoffs to engineering and product leaders.
Nice To Haves
- Experience with long-running agent workflows that search or read documents.
- Experience with a vector store at production scale.
- Experience processing large confidential documents and data tables.
- Experience with hybrid search, citations, and retrieval-quality evaluation.
- Experience with virtual data rooms, M&A documents, or similar document-heavy work.
- Experience building tool interfaces that expose search to an agent.
Responsibilities
- Own retrieval for agents working on live deals and balance answer quality, speed, and cost.
- Scale platform processing of large documents and data tables so agents can find and reason over content that does not fit in one pass.
- Shape and evolve agent context as deal workflows become longer and more complex.
- Build search tools agents call, covering both indexed and not-yet-indexed content and returning trustworthy snippets, citations, and locations.
- Keep agent context aligned with the data room and access permissions so agents cannot read content users cannot access.
- Determine when a model may answer from retrieved context and when the product must check the result.
- Mentor engineers and set technical direction for retrieval across teams.
Benefits
- Health insurance (medical, dental, and vision)
- Retirement savings plan
- Paid time off
- Other employee benefits
- The position may be eligible for bonuses, commissions, or overtime if applicable.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
