Demonstrated experience shipping stateful, policy-controlled agent runtimes and tool-using multi-agent systems for autonomous long-horizon work: durable session lifecycle, context-window management, retrieval and RAG, structured outputs, guardrails, evaluation systems, secure delegation, safe tool use, interruption handling, and recovery—built on established orchestration frameworks or on custom infrastructure of your own design, including MCP and production tool and integration lifecycle management. What you will bring 8+ years of hands-on software, machine learning, or applied AI engineering experience with Staff/Principal-level technical impact across teams—capable of independently taking a frontier-grade, full-stack agentic product from prototype to production (agent runtime, CLI/TUI, web frontend, backend services and APIs, and the underlying data layer) while remaining deeply involved in code, design, delivery, and production operations.