Staff AI Engineer

Role overview Set technical direction for production AI agent systems and build the shared engineering foundations that make them reliable, secure and cost-aware. This hands-on staff-level role works across engineering, product, research and security, helping teams move from prototypes to dependable systems and improve their use of AI coding agents.

Responsibilities - Guide agent architecture, including orchestration, tool use, context and memory, human oversight and recovery from failures. - Build and operate shared capabilities for evaluation, observability, tracing, execution controls and model access with routing or failover. - Create representative evaluations for task success, accuracy, false positives, security and cost; turn production failures into regression tests. - Improve resilience to tool errors, timeouts, rate limits and partial execution, with clear limits on retries, runtime and spend. - Work with security and platform teams on scoped permissions, customer data isolation, audit trails and safe tool and code execution. - Set engineering practices for CI evaluations, prompt and model versioning, regression checks, cost and latency budgets, and staged releases. - Benchmark models and guide quality, latency and cost trade-offs; support production readiness and incident investigation. - Mentor engineers and help teams apply AI coding agents across planning, implementation, review and testing.

Requirements - Typically 8–10 or more years of software engineering experience, with technical leadership across teams. - Hands-on experience building and operating LLM-based agents in production and improving their reliability against measurable goals. - Strong knowledge of agent design, including tool use, orchestration, planning, context and memory management, and when simpler workflows are preferable. - Experience operating LLM workloads through cloud model platforms or provider APIs, including cost tracking, rate limits and failure handling. - Strong backend and distributed systems fundamentals, including APIs, asynchronous work, concurrency and fault tolerance. - Experience with production observability, incident response and safe rollouts; understanding of prompt injection, unsafe tool execution and sensitive-data exposure risks. - Evidence of impact beyond individual contributions, such as shared platforms, improved engineering standards or mentoring.

Nice to have - Experience introducing AI coding tools across engineering teams and measuring their effects, or contributions to agent engineering through writing, talks or open source.

Benefits and work setup - Compensation includes salary, equity and benefits. The listed salary range is $200,000–$240,000, with variation by location and candidate qualifications. - Benefits include retirement savings, healthcare coverage, stipends for wellness, home-office equipment and learning, plus paid time off and parental leave.