About The Position

This full-time, W-2 role is for a board-certified physician to work directly with research and program management teams at a leading AI lab. The physician will apply independent clinical judgment to evaluate AI-generated medical content, develop clinical benchmarks, and establish reference solutions that define accurate, safe, and evidence-based medical reasoning. The role is intended for practicing physicians with substantial post-residency experience and strong expertise in a clinical specialty. The physician will collaborate with AI researchers, engineers, and specialists to improve the quality, reliability, and clinical relevance of advanced AI systems. Work is hybrid in the San Francisco Bay Area, with on-site collaboration multiple days per week as required. The position is a 40-hour-per-week initial six-month engagement. Client-issued accounts and equipment will be provided, and work will take place within the client's internal tools and research environment. Candidates must live in the San Francisco Bay Area or relocate before the engagement begins; relocation expenses are the candidate's responsibility, and relocation assistance is not provided.

Requirements

  • MD or DO degree from an accredited medical school.
  • Completed residency training in a recognized medical specialty.
  • At least 4 years of independent clinical practice after residency; residency and fellowship training do not count toward this requirement.
  • Active, unrestricted medical license in at least one US state.
  • Current board certification in the candidate's specialty.
  • Demonstrated expertise in a defined clinical specialty or subspecialty.
  • Clear professional progression into senior clinical responsibilities, such as Attending Physician, Medical Director, Division Chief, Associate Professor, Professor, or Chief Medical Officer.
  • Proven ownership of clinical decisions and experience applying independent medical judgment in patient care.
  • Practical experience using large language models (LLMs) in a professional setting and ability to distinguish clinically sound reasoning from plausible but medically incorrect responses.
  • Excellent written communication skills and ability to explain complex clinical concepts through precise, well-structured feedback.
  • Ability to commit reliably to 40 hours per week for the initial six-month engagement.
  • Must currently reside in the San Francisco Bay Area or be willing to relocate before the engagement begins, at the candidate's expense.
  • Must be available for regular on-site collaboration multiple days per week; the role is not fully remote.

Nice To Haves

  • Experience in utilization management, clinical informatics, medical affairs, or clinical quality assurance.
  • Experience developing clinical guidelines, medical protocols, or evidence-based evaluation frameworks.
  • Previous involvement in medical research, clinical education, or multidisciplinary healthcare initiatives.
  • Familiarity with AI model evaluation, clinical benchmark development, or medical dataset quality assessment.

Responsibilities

  • Review and evaluate clinical knowledge tasks and AI-generated medical responses, identifying gaps in clinical reasoning, missing considerations, unsafe recommendations, and deviations from established medical guidelines.
  • Develop detailed task specifications, create accurate reference answers, and design clinical problems reflecting real-world medical practice and decision-making.
  • Design challenging, specialty-specific clinical tasks and evaluation datasets to measure the accuracy, depth, safety, and reliability of AI-generated medical reasoning.
  • Assess AI responses across diagnosis, treatment planning, patient management, clinical guidelines, and specialty-specific medical scenarios.
  • Provide clear, structured, actionable written feedback to help research teams identify weaknesses and improve model performance.
  • Collaborate with AI researchers, engineers, and specialists from adjacent domains to establish consistent evaluation standards and translate clinical expertise into measurable assessment criteria.
  • Help develop medicine-specific evaluation frameworks, tools, and workflows to ensure AI outputs meet professional clinical standards.

Benefits

  • Client-issued accounts and equipment will be provided.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume

What This Job Offers

Job Type

Full-time

Career Level

Senior

Education Level

Ph.D. or professional degree

© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service