Part-Time Clinical AI Evaluation Physician (MD/DO)

Mindrift; Comisión de Fomento de Perú; Remote; ARS 104,929,000 - 149,444,000; Part time

Job summary

Mindrift is seeking US-based physicians to evaluate clinical EHR vignettes for a medical AI evaluation program. This project-based, part-time role focuses on testing, evaluating, and improving AI-driven clinical reasoning.

Contributors will score vignette accuracy and completeness, assess whether the reasoning leads to the correct answer, and write short rationales. The work uses three blind reads followed by physician adjudication.

Compensation is paid per accepted task, with rates up to $60/hr.

Qualifications

• MD or DO medical degree and an active US license.
• Board certification or completed residency with recent direct patient care.
• Broad, multi-system diagnostic and treatment experience.
• Strong clinical reasoning and application of evidence‑based guidelines.
• Prior experience in medical AI evaluation or medical annotation/QA is a plus.
• Strong written English (C1+)

Responsibilities

• Evaluate clinical EHR vignettes paired with questions, proposed answers, and distractors across multiple body systems.
• Score the clinical reasoning quality, vignette accuracy, completeness, and trap quality.
• Check whether reasoning reaches the answer from vignette facts and write short rationales.
• Participate in three independent blind reads, followed by physician adjudication.
• Contribute to improving AI tools used in medical evaluation.

Skills

MD or DO medical degree

Active US medical license

Board certification or residency

Clinical reasoning

Medical AI evaluation experience

Excellent English writing (C1+)

Education

MD/DO degree

Job description

Mindrift is seeking US-based physicians to evaluate clinical EHR vignettes for a medical AI evaluation program. This project-based, part-time role focuses on testing, evaluating, and improving AI-driven clinical reasoning.

Contributors will score vignette accuracy and completeness, assess whether the reasoning leads to the correct answer, and write short rationales. The work uses three blind reads followed by physician adjudication.

Compensation is paid per accepted task, with rates up to $60/hr.