Staff AI Engineer

Role overview Provide hands-on technical leadership for production AI products and the shared platform beneath them. You’ll contribute to live systems early, lead major initiatives from design through launch, and shape architecture and engineering practices across teams. The work calls for measurable improvements in quality and reliability, with customer-facing features that need to operate dependably in real use.

Responsibilities - Design, build, and improve production LLM features, including conversational systems, AI-generated drafts, and shared context services. - Lead AI initiatives through architecture review, cross-functional development, launch, and follow-up, including the evaluations and safeguards needed for operation. - Diagnose known failure modes and improve quality, reliability, and evaluation coverage using measurable results. - Build shared evaluation, guardrail, and observability practices to detect regressions before release and monitor behavior in production. - Make architectural proposals and guide major decisions for AI systems and shared infrastructure. - Own broader engineering initiatives, such as evaluation standards, code review practices, or documentation improvements.

Requirements - Staff-level experience leading ambiguous, cross-team engineering work as a hands-on individual contributor, including delivery and architectural tradeoffs. - Proven experience designing and shipping LLM agents or generative features used by customers in production. - Experience building production AI evaluation systems that combine automated tests, traces, human feedback, and monitoring. - Strong judgment about when to use deterministic code versus an LLM, and how to design safe tools and human handoffs. - Ability to manage reliability, security, latency, and cost tradeoffs and make pragmatic model-provider and build-versus-buy decisions. - Backend and platform engineering experience, including Python, Django, PostgreSQL, Redis, asynchronous workers, and REST or GraphQL APIs.

Benefits and work setup - High ownership and influence over AI architecture, product direction, and shared platform decisions. - Work spans multiple AI products and draws on clinical and practice data from a network of about 1,200 medspas. - Competitive salary; an inclusive workplace and interview accommodations are described.