Staff Software Engineer
Posted Updated
Description
- 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 dealmakers
- 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 ephemeral 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
Benefits
- Culture and benefits built around work-life balance
- Extensive resources to support physical and mental health
- Employee assistance program
- Generous retirement plans
- Incentives for referring new colleagues
- Learning, training and mentoring programs
- Cross-functional projects
- Stretch assignments to help you progress
- Receive feedback and earn bonuses from peers & managers
- Employee bonding activities
- ESG and charitable team initiatives
- Experience developing production LLM applications involving tool calling, multi-step workflows, retrieval, agent orchestration, or context management
- Ability to influence technical strategy, mentor senior engineers, and communicate complex tradeoffs clearly to engineering and product leaders
- Deep expertise in backend platforms, distributed systems, asynchronous execution, APIs, fault tolerance, and stateful services
- Experienced in building and operating production software, with a track record of leading complex technical initiatives across teams
- Strong hands-on Python proficiency and experience with a modern language such as TypeScript, Java, Go, Kotlin, or Rust
- Excellent product and architectural judgment: able to evaluate emerging techniques, balance speed with reliability, and turn ambiguous problems into maintainable platforms
- 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
- Custom agent runtimes or orchestration frameworks; agentic coding systems or autonomous development environments
- Persistent or hierarchical agent memory, context engineering, retrieval architectures, or long-running agent workflows
- Secure code execution, sandboxing, Docker, Kubernetes, microVMs, or ephemeral compute
- Multi-agent coordination, MCP servers, tool registries, capability-based permissions, model routing, or agent evaluation and tracing
- Enterprise SaaS, M&A, virtual data rooms, regulated data, financial services, or complex document-centric workflows
Skills
Sign in to read and join the discussion.