Physician (MD/DO) - Medical AI Evaluation

Mindrift; South Carolina; On-site; USD 34,000 - 179,000; Part time

Job summary

Mindrift seeks US-based physicians (MD/DO) to evaluate clinical EHR vignettes for a medical AI evaluation program focused on general and internal medicine. Tasks involve reviewing vignette questions, proposed answers, and distractors, then scoring reasoning quality and vignette accuracy.

You will write concise rationales and participate in blinded reads with adjudication, improving AI tools used in healthcare.

Qualifications

• MD or DO with active US medical license.
• Board certification or completed residency in internal, family, emergency, or hospital medicine.
• Experience in evaluating medical AI content, clinical annotation, or QA is a plus.
• Excellent written English skills (C1+).

Responsibilities

• Evaluate clinical EHR vignettes paired with a question, a proposed answer, and a distractor “trap” answer across multiple medical domains.
• Score the clinical reasoning quality of benchmark items and assess vignette accuracy and trap quality.
• Write short rationales explaining conclusions and participate in physician adjudication.
• Work through three independent blind reads to ensure consistency and accuracy.
• Contribute to improving AI tools through careful evaluation and feedback.

Skills

Active US medical license

Board certification or residency

Broad multi-system diagnostic and care

Strong clinical reasoning

Medical AI evaluation/annotation

Excellent written English

Education

MD/DO degree

Board certification or residency

Job description

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation isproject-based.

What this opportunity involves

We’re looking for US-based, actively practicing physicians (MD/DO) to evaluate clinical EHR vignettes for a medical AI evaluation program. General and internal medicine are our main focus. While each project involves unique tasks, contributors may:

• Evaluate clinical EHR vignettes paired with a question, a proposed answer, and a distractor “trap” answer across diagnosis and treatment tasks, spanning cardiovascular, nervous, hematologic, respiratory, digestive, urinary, reproductive, musculoskeletal, and integumentary systems;
• Score the clinical reasoning quality of benchmark items: vignette accuracy and completeness, whether the vignette gives the answer away, answer correctness and gradeability, and trap quality;
• Check whether the reasoning chain reaches the answer from vignette facts alone, correct reasoning traces, and write short rationales;
• Work within three independent blind reads, followed by physician adjudication. Real clinical complexity only. You’re improving the AI tools you’ll eventually use yourself.

What we look for

This opportunity is a good fit for US-based physicians open to part-time, non-permanent projects. Ideally, contributors will have:

• Medical degree (MD or DO) and an active, unrestricted US medical license (verified with the issuing medical board);
• Board certification or completed residency training, with recent direct patient care (attending-level preferred);
• Broad, multi-system diagnostic and treatment experience (internal, family, emergency, or hospital medicine);
• Strong clinical reasoning: differential diagnosis, next-step management, and application of evidence-based guidelines;
• Prior experience in medical AI evaluation, clinical content or exam-question review, or medical annotation/QA (a plus);
• Strong written English (C1+).

This opportunity is not fit to medical students, unlicensed medical graduates, non-physician clinicians (NPs, PAs, nurses, pharmacists), or non-clinical healthcare titles.

Project time expectations

For this project, tasks are estimated to require around 10-20 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.

Compensation

Paid per accepted task. Your rate depends on the qualification tier you reach and how efficiently you complete tasks — up to the equivalent of$130/hr . Because payment is per approved task, a faster pace raises your effective hourly rate.