3 days ago
Minneapolis, MN, USA or New York, NY, USAStaff+
Base Salary
$170k - $297k/yr
Responsibilities
- Lead the architecture and evolution of the custom agent harness, including reasoning loops, planning, tool selection, state transitions, structured outputs, and runtime controls.
- Design layered agent memory with retrieval, consolidation, compaction, provenance, retention, and access controls.
- Architect isolated, containerized execution environments with tenant boundaries, resource quotas, restricted networking, and secure credential handling.
- Build resilient orchestration for asynchronous tasks, subagents, delegation, checkpoints, resumability, retries, failure recovery, and human approvals.
- Create secure 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 for quality, correctness, reliability, latency, and cost.
- Partner across Product, Machine Learning, Security, and platform teams and mentor engineers while contributing to critical implementations.
Requirements
- Experience building and operating production software and 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 plus experience with a modern language such as TypeScript, 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.
- Strong product and architectural judgment, including the ability to 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.
- Preferred experience includes custom agent runtimes, agentic coding systems, persistent or hierarchical agent memory, retrieval architectures, secure code execution, sandboxing, Docker, Kubernetes, microVMs, multi-agent coordination, MCP servers, tool registries, capability-based permissions, model routing, agent evaluation and tracing, or enterprise SaaS and regulated data workflows.
Benefits
- Health insurance including medical, dental, and vision coverage.
- Retirement savings plan, paid time off, and other employee benefits.
- Hybrid work based in New York City or Minneapolis, with in-office collaboration on Mondays, Tuesdays, and Thursdays.
- The position may be eligible for bonuses, commissions, or overtime if applicable.
Categories
About Datasite
Datasite builds SaaS tools for mergers and acquisitions, centered on secure virtual data rooms, deal preparation, diligence, and marketing workflows. Its platform is used by investment banks, private equity and venture investors, law firms, and corporate development teams to manage confidential documents, automate redaction, track buyers, and run deals. Founded in 1968 and headquartered in Minneapolis, it is privately held and part of CapVest’s portfolio.