About the role
Clara is building the first AI-first medical practice from the ground up. We're reimagining primary care and providing patients with deep insights and immediate diagnosis and treatment in ways not previously possible.
Clara's founders have built and scaled a previous telemedicine company to over $100m in revenue and we're funded by top investors.
This is a mission-driven, high-performance team at the forefront of healthcare and AI, working in person in San Francisco 5 days per week. We will assist with relocation and work visas for the right candidate.
What you'll build
You'll own Clara's AI brain - the LLM-powered system that enables immediate diagnosis and treatment. This isn't chatbot work; it's medical AI that needs to be accurate, safe, and cost-effective at scale.
Your responsibilities
LLM integration & optimization (50%):
- Build and optimize LLM integration for medical insights, diagnosis and treatment
- Implement streaming chat responses with proper error handling
- Manage context windows for complex medical conversations
- Optimize prompt engineering for clinical accuracy and safety
- Control LLM costs through model selection, caching, and prompt efficiency
AI infrastructure (30%):
- Build semantic search and RAG systems
- Implement vector similarity search for medical record retrieval
- Design memory systems for patient conversation context
- Build evaluation framework for groundedness, safety, and correctness
Medical AI safety (20%):
- Ensure AI responses are medically grounded (no hallucinations)
- Implement guardrails for high-risk medical scenarios
