This role sits at the core of an early-stage healthtech marketplace, owning the agent infrastructure that powers both patient-facing and internal AI systems. You will design and build the orchestration layer, tool integrations, retrieval pipelines, and evaluation frameworks that automate clinic-side and internal operations end-to-end. This is a systems and infrastructure role, distinct from live conversation AI work, and your output will directly shape how the company scales.
What You’ll Do
•
Design and implement the orchestration layer for multi-step agentic workflows across clinic operations and internal processes.
•
Integrate external tools and APIs into agent systems, ensuring reliable tool calling and robust error handling.
•
Build retrieval and evaluation infrastructure to measure and continuously improve agent reliability and accuracy.
•
Identify recurring manual workflows and ship automation systems to eliminate them.
•
Monitor agent performance in production and iterate on system design based on real-world behavior.
What We’re Looking For
•
Demonstrated experience building agent or LLM systems through professional work, personal projects, research, or open-source contributions, covering areas such as orchestration, tool integrations, RAG, or evals.
•
Strong math and computer science fundamentals, evidenced by an elite academic record, competition experience, or fast self-directed learning in technical domains.
•
Experience designing and implementing agent orchestration systems or multi-step workflows.
•
Experience integrating tools, APIs, or external services into agent systems.
•
Experience building or working with retrieval-augmented generation (RAG) systems.
•
Experience designing evaluation frameworks or monitoring systems for agent reliability.
•
An automation instinct: you naturally spot recurring manual work and think in systems.
•
Ability to work effectively in a small, early-stage team with limited resources.
•
Bonus: experience with healthcare or regulated industry systems, prompt engineering, LLM fine-tuning, or open-source AI contributions.
•
No prior professional experience required; recent graduates and self-taught builders are welcome.
Compensation & Benefits
Base salary of $150,000 to $200,000 annually, plus meaningful equity. Visa sponsorship is not available.
Location
Full-time, on-site in San Francisco, California, five days per week.