About this role
Drive the evaluation and improvement of clinical reasoning in medical AI systems by working with research teams to design realistic assessments, create clinical scenarios, and translate clinical expertise into measurable evaluation methods.
Key Responsibilities- Design systematic evaluation frameworks to measure AI performance on clinical tasks
- Create clinical scenarios that probe reasoning, diagnostic thinking, and decision making
- Develop assessment methods that capture the nuance of real-world clinical practice
- Identify gaps in AI medical knowledge and clinical reasoning
- Collaborate closely with AI researchers to iterate on model performance based on evaluation findings
- Licensed physician in active clinical practice, any specialty
- Experience with clinical decision making and applying evidence based medicine
- Demonstrated interest in how AI can support clinical practice
- Strong analytical skills and clear written and verbal communication
- Engagement type: contract
- Location: remote
- Commitment: flexible engagement, up to 30 hours per week, with scheduling flexibility to accommodate clinical duties
- Duration: initial 1 month engagement, with potential extension based on performance and fit
Candidates must be a licensed physician currently in active clinical practice. No additional work authorization information is provided in the source material.
Why It MattersThis role shapes the next generation of medical AI by ensuring systems can handle the complexity of real clinical practice while enabling remote, flexible collaboration alongside ongoing clinical work.