5 hours ago
Base Salary
$150k - $220k/yr
Responsibilities
- Diagnose failures in patient-facing AI conversations and ship code fixes to prevent recurrence.
- Build and maintain agent infrastructure, including tool integrations, evaluation frameworks, and retrieval systems.
- Automate recurring clinic-operations workflows through code.
- Handle difficult patient-facing situations with care and turn them into product insights.
- Own systems end-to-end and make architectural and implementation decisions independently.
Requirements
- Demonstrated ability to build and ship LLM or agent systems end-to-end through professional experience, personal projects, research, or open-source contributions.
- Hands-on experience with agent infrastructure, including evaluations, RAG, retrieval systems, and tool integrations.
- Proficiency in Python or an equivalent programming language.
- Strong computer science and mathematics fundamentals; top-tier university degrees, published research, or math competition experience are preferred.
- Ability to identify recurring manual workflows and eliminate them through automation.
- Comfort owning systems independently in a fast-moving startup environment.
- Patient-facing warmth and empathy for handling difficult conversations and extracting product insights.
- Familiarity with vector databases, embedding systems, or semantic search is preferred.
- Experience with prompt engineering, fine-tuning, or conversational AI evaluation is preferred.
- Existing US work authorization is required.
Benefits
- Full-time, on-site role in San Francisco, California, five days per week with no remote exceptions.
- Salary range of $150,000 to $220,000 USD annually.