Principal AI Product Engineer

Own the end-to-end architecture and delivery of production AI products, from AI backend and APIs through to user-facing applications. Design and establish scalable RAG architectures and Agentic AI workflows, including tool use, planning and human-in-the-loop patterns. Define AI-native engineering practices, including the use of coding agents, reusable components, development frameworks and evaluation tooling. Build and guide the development of production backend services using Python and modern API technologies. Develop reliable AI applications that effectively handle streaming, failures, latency and other real-world production requirements. Establish strong evaluation practices across grounding, retrieval quality, regression detection and production performance. Define reusable technical standards, reference architectures and components that can be adopted across multiple AI products. Provide technical leadership through architecture reviews, engineering standards and mentorship while remaining highly hands-on with delivery.

Desired Candidate Profile

Proven experience operating at Staff, Principal or equivalent senior IC level, with a strong track record of shipping production systems used by real users. Strong Python engineering skills with substantial hands-on experience building LLM- powered applications in production. Deep experience with RAG, retrieval pipelines, Agentic AI, agent orchestration and AI backend services. Strong understanding of LLM behaviour and failure modes, including hallucination, context degradation, latency and model evaluation. Experience owning AI products end-to-end across backend services, APIs and user- facing interfaces. Hands-on experience with modern Agentic AI and LLM frameworks such as LangChain, LangGraph or similar technologies. Comfortable working across a modern technology stack, including React, APIs, PostgreSQL, Docker, cloud environments and CI/CD. Experience with AI evaluation frameworks, including retrieval quality, grounding, regression testing and offline/online evaluation. Strong experience using AI coding agents and AI-native development approaches as part of day-to-day software engineering. Experience designing reusable engineering standards, tooling and architectures that improve how wider engineering teams build AI products.