Licensed Physician for AI Model Evaluation

Lead the clinical evaluation of medical AI by designing and executing assessments that probe clinical reasoning and decision-making. Work directly with research teams to create realistic clinical problems, find where models fail or lack medical knowledge, and shape improvements so AI systems align with real-world clinical practice. This is a remote, contract role with flexible scheduling to accommodate active clinical duties.

Based in San Francisco, the organization accelerates frontier AI research and helps enterprises move advanced AI from prototype to reliable, production-ready systems by combining high-quality data, training pipelines, and expert research collaboration.

• Design systematic evaluation frameworks for medical AI systems
• Create clinical scenarios that test AI reasoning and decision-making capabilities
• Develop assessment methods that capture the nuance of clinical practice
• Identify gaps in AI medical knowledge and clinical reasoning
• Collaborate with AI researchers to iterate on model performance and evaluation design

• Licensed physician in active clinical practice, any specialty
• Demonstrated experience with clinical decision-making and evidence-based medicine
• Interest in how AI can support clinical practice and patient care
• Strong analytical thinking and clear written and verbal communication skills

• Location: Remote
• Engagement type: Contract
• Time commitment: Flexible engagement, up to 30 hours per week
• Duration: 1 month, with potential extensions based on performance and fit
• Schedule: Flexible scheduling to accommodate ongoing clinical responsibilities

• Must be a licensed physician actively practicing medicine, any specialty
• Ability to participate remotely and commit up to 30 hours per week within the stated engagement period