Resident Medical Specialist (MD/DO)

Remote | Contractor | Up to 30 hours/week | 1-month engagement

About the Role

We are seeking licensed physicians in active clinical practice to work with research teams evaluating and improving how AI systems handle clinical reasoning, medical decision-making, and real-world healthcare scenarios.

You’ll use your medical expertise to design structured evaluations, develop realistic clinical scenarios, identify gaps in AI medical knowledge and reasoning, and help assess whether AI systems can appropriately handle the complexity and nuance of clinical practice.

The role is well suited to physicians who enjoy critical thinking, problem solving, evidence-based medicine, and evaluating how AI approaches medical problems.

What You’ll Do

• Design systematic evaluation frameworks for medical AI systems.

• Create clinical scenarios that test AI reasoning and medical decision-making.

• Develop assessment methods that capture the nuance of real clinical practice.

• Identify gaps in AI medical knowledge, reasoning, and clinical performance.

• Collaborate with AI research teams to evaluate and improve model performance.

Requirements

• MD or DO with an active medical license and current clinical practice.

• Experience with clinical decision-making and evidence-based medicine.

• Strong critical-thinking and problem-solving skills.

• Strong analytical and communication abilities.

• Interest in how AI can support and enhance clinical practice.

Relevant clinical expertise may include areas such as pediatrics, emergency medicine, obstetrics and gynecology, gynecologic oncology, public health, and other medical specialties.

Work & Engagement

• Fully remote contractor engagement

• Flexible scheduling around clinical commitments.

• Up to 30 hours per week.

• Initial duration of 1 month.

• Potential extensions based on performance and fit.

Why This Opportunity

Bring your clinical judgment into the development and evaluation of medical AI systems. Your expertise will help test whether AI can reason through realistic medical problems with the level of nuance, evidence-based thinking, and clinical judgment required in practice.