Turn chat into an operator that acts on live operations. Role shape: End-to-end product ownership with a focus on the agentic layer: lower the barrier to using the platform and let coordinators create and run operational workflows from chat. Environment: TypeScript, Python, Postgres, AWS, agentic AI and tool use, SQL and structured data access, frontline communication channels, evaluation harnesses, on-site deployment, customer management. Experience: Minimum three years in production full-stack engineering, including shipped LLM-powered product work. Practical reality: direct customer contact, time in live operations starting on the airport ramp, coding credits, London-based, remote only by exception, UK work authorization preferred. What We Are Looking For: You own the product end to end, from the TypeScript interface a coordinator uses under pressure to the Python services and agent tooling behind it: The tool layer over Kyber's operational model; Structured data access; Workflow creation and execution from chat; Communication out to frontline staff; Exception handling; The evaluation harness that keeps it honest as models and prompts change. At least three years shipping production full-stack software... London-based, remote only by exception. UK work authorization preferred.