About the Role
This is a hands-on engineering role at an early-stage healthtech marketplace that connects patients with vetted international clinics for affordable medical care. You will own the patient-facing AI conversation loop end-to-end, diagnosing failures in production and shipping fixes that directly improve patient outcomes. The role sits at the intersection of agent infrastructure and real-world empathy, making it both technically challenging and genuinely meaningful.
What You'll Do
Diagnose why AI conversations with patients fail and ship code fixes to prevent recurrence.
Build and maintain agent infrastructure including tool integrations, evaluation frameworks, and retrieval systems.
Automate recurring manual workflows on the clinic operations side, eliminating toil through code.
Handle patient-facing situations with care when the AI falls short, turning those moments into product insights.
Own systems end-to-end with minimal oversight, making architectural and implementation decisions independently.
What We're Looking For
Demonstrated ability to build and ship LLM or agent systems end-to-end; professional experience, personal projects, research, or open-source contributions all count equally.
Hands-on experience with agent infrastructure: evals, RAG and retrieval systems, and tool integrations.
Proficiency in Python or an equivalent language for building agent and automation infrastructure.
Strong computer science and mathematics fundamentals; elite academic signals such as top-tier university degrees, published research, or math competition experience are a strong plus.
Automation instinct: you spot recurring manual workflows and proactively eliminate them through code.
Comfort owning systems end-to-end with minimal oversight in a fast-moving startup environment.
Patient-facing warmth and empathy for handling difficult conversations and extracting product lessons from them.
Familiarity with vector databases, embedding systems, or semantic search is a plus.
Experience with prompt engineering, fine-tuning, or conversational AI evaluation is a plus.
Existing US work authorization required; no visa sponsorship available.
Compensation & Benefits
Salary range: $150,000 to $220,000 USD annually. No visa sponsorship is available; existing US work authorization is required.
Location
Full-time, on-site in San Francisco, California, five days per week. No remote exceptions.