Part-Time MD/DO for Medical AI Evaluation Projects

Mindrift; Clifton (TX); À distance; USD 80 000 - 113 000; Temps partiel

Résumé du poste

Mindrift invites US-based physicians (MD/DO) to participate in an AI evaluation program. This is a part-time, project-based opportunity focusing on testing, evaluating, and improving AI systems using clinical EHR vignettes across multiple medical domains.

Contributors will perform structured evaluations, score clinical reasoning, and provide concise rationales. Compensation is task-based, with rates up to $70/hr, reflecting efficiency and accuracy.

Qualifications

• Medical degree (MD or DO) and active, unrestricted US medical license.
• Board certification or completed residency training with recent direct patient care.
• Broad, multi-system diagnostic and treatment experience across internal, family, emergency, or hospital medicine.
• 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+).

Responsabilités

• Evaluate clinical EHR vignettes paired with a question, proposed answer, and distractor across multiple organ systems.
• Score the clinical reasoning quality of benchmark items including vignette accuracy, completeness, and trap quality.
• Check whether the reasoning chain reaches the answer from vignette facts and write short rationales.
• Work within three blind reads, followed by physician adjudication.

Connaissances

MD/DO degree

Active US medical license

Board certification or residency

Strong written English

Clinical reasoning

Medical AI evaluation experience

Formation

MD or DO

Board certification / residency training

Description du poste

Mindrift invites US-based physicians (MD/DO) to participate in an AI evaluation program. This is a part-time, project-based opportunity focusing on testing, evaluating, and improving AI systems using clinical EHR vignettes across multiple medical domains.

Contributors will perform structured evaluations, score clinical reasoning, and provide concise rationales. Compensation is task-based, with rates up to $70/hr, reflecting efficiency and accuracy.