12 hours ago
San Francisco, CA, USAMid Level
Base Salary
$150k - $200k/yr
Responsibilities
- Diagnose failures in patient-facing AI conversations and ship code fixes to prevent recurrence.
- Build and maintain agent infrastructure, tool integrations, evaluation frameworks, and retrieval systems.
- Automate recurring manual clinic workflows through code.
- Handle patient-facing situations with empathy when the AI falls short and translate those interactions into product insights.
- Own systems end to end and make architectural and implementation decisions independently.
Requirements
- At least 2 years of demonstrated experience building and shipping LLM or agent systems through professional work, personal projects, research, or open source.
- Hands-on experience with agent infrastructure, including evaluations, RAG or retrieval systems, and tool integrations.
- Proficiency in Python or an equivalent programming language.
- Strong computer science and mathematics fundamentals.
- Ability to diagnose and fix failures in production LLM or agent systems.
- Patient-facing warmth and empathy, with comfort handling difficult conversations carefully.
- Ability to work autonomously in a fast-moving startup environment.
- Experience with vector databases, embedding systems, semantic search, prompt engineering, fine-tuning, or conversational AI evaluation is a plus.
- Top-tier university background, published research, or mathematics competition experience is a strong plus.
- Existing US work authorization is required.
Benefits
- Base salary of $150,000 to $200,000 USD annually.
- Fully on-site in San Francisco, California, five days per week, with no remote exceptions.
- Visa sponsorship is not available.