Software Engineer, AI Agent Platform & Runtime

About us Datasite is the essential infrastructure for M&A. Also comprising Grata, Blueflame AI, and Sherpany, we help deal breakers find opportunities, manage transactions, and make key decisions. Whatever your talents, you can find a place for them here. Get involved in some of the biggest business ventures today. Work with other gifted people around the world. Follow your ambitions, or discover a whole new path.

Can you help us simplify the complex, create great experiences, and deliver better outcomes? Then let's talk.

Why Engineering at Datasite Datasite's engineering organization builds the software the world's deal makers depend on to find, evaluate, negotiate, and close transactions: secure virtual data rooms, AI-assisted diligence, deal sourcing, and private-company intelligence. We're looking for a hands-on Staff Software Engineer to shape the foundational infrastructure for enterprise AI agents. You'll evolve our custom agent harness, build layered memory and secure isolated execution, and make sophisticated agent workflows dependable at production scale.

This is an opportunity to solve challenging problems in distributed systems, applied AI, security, and platform engineering - not simply wrap APIs around models. Help define how agents reason, plan, remember, use tools, delegate work, and recover from failures across complex, high-stakes business workflows. You'll own architecture decisions and collaborate across Engineering, Product, Machine Learning, and Security to deliver meaningful capabilities for deal makers.

We are hiring in New York City and Minneapolis. Datasite is a hybrid company, with in-office collaboration on Mondays, Tuesdays, and Thursdays.

• Lead the architecture and evolution of Datasite's custom agent harness, including reasoning and execution loops, planning, tool selection, state transitions, structured outputs, and runtime controls.
• Design layered agent memory spanning working context, episodic history, semantic knowledge, and durable workflow state; build retrieval, consolidation, compaction, provenance, retention, and access controls.
• Architect isolated, containerized agent execution environments for code, files, and tools, with ephemer workloads, tenant boundaries, resource quotas, restricted networking, and secure credential handling.
• Build resilient agent orchestration: asynchronous tasks, specialized subagents, delegation, checkpoints, resumability, retries, failure recovery, and human approvals.
• Create secure, extensible tool integrations using MCP and related interfaces, with authentication, authorization, least-privilege permissions, and safeguards against prompt injection and unsafe actions.
• Establish agent evaluation, tracing, observability, and regression testing to measure task quality, correctness, reliability, latency, and cost; drive measurable improvements.
• Make high-impact technical tradeoffs between probabilistic model behavior and deterministic application logic, validation, or human review.
• Partner with Product, Machine Learning, Security, and platform teams to turn diligence, research, and deal workflows into production-grade agent experiences; mentor engineers while remaining hands-on in critical implementation.

• Experienced in building and operating production software, with a track record of leading complex technical initiatives across teams.
• Deep expertise in backend platforms, distributed systems, asynchronous execution, APIs, fault tolerance, and stateful services.
• Strong hands-on Python proficiency and experience with a modern language such as Type Script, Java, Go, Kotlin, or Rust.
• Experience developing production LLM applications involving tool calling, multi-step workflows, retrieval, agent orchestration, or context management.
• Practical understanding of containers, cloud-native infrastructure, workload isolation, and secure execution patterns.
• Strong foundations in data persistence, caching, event-driven architectures, permissions, multi-tenancy, and secrets management.
• Excellent product and architectural judgement: able to evaluate emerging techniques, balance speed with reliability, and turn ambiguous problems into maintainable platforms.
• Ability to influence technical strategy, mentor senior engineers, and communicate complex tradeoffs clearly to engineering and product leaders.

• Custom agent runtimes or orchestration frameworks; agentic coding systems or autonomous development environments.
• Persistent or…