Program evaluation Jobs in Dallas, TX

About the company

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. This is a task-based, independent contractor opportunity, not an employment relationship. Participation is limited to this project.

Project Highlights

• Earnings per approved task: a fixed rate for each task, set in advance
• Fully self-scheduled: no minimum hours and no set schedule; you choose which tasks to take and when
• Remote: open to US-licensed physicians based in eligible US states
• No patient contact, no malpractice exposure: you review written clinical cases
• All contributors are license-verified physicians
• $50 one-time onboarding reward, paid once your first task on the project is approved

What this project involves

We're looking for physicians (MD/DO) with an active, unrestricted US medical license to evaluate clinical EHR vignettes for a medical AI evaluation project. General and internal medicine are the main focus. Each task is a written clinical case, assessed against the project's acceptance criteria. 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.

Each case receives 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 project is a good fit for US-licensed physicians looking for a flexible, time-limited project they can fit around their other commitments. Ideally, contributors will have:

• Medical degree (MD or DO) and an active, unrestricted US medical license (verified at onboarding and re-checked monthly);
• Board certification or completed residency training, with direct patient care experience (attending-level preferred). Practising or retired physicians welcome;
• 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 project is not suitable for medical students, unlicensed medical graduates, non-physician clinicians (NPs, PAs, nurses, pharmacists), or non-clinical healthcare titles.

How it works

Apply → Pass qualification(s) → Join the project → Complete tasks → Get paid for approved tasks

Flexibility

You decide whether, when, and how much to contribute. There are no minimum hours, set schedules, or required availability. Task availability varies with project phases. Tasks are submitted through the platform and are approved when they meet the project’s acceptance criteria.

Earnings

Earnings are paid only for completed and approved tasks. Each task type has a fixed rate. There is no time tracking and no hour logging. There are no tiers or speed adjustments to the rate. QA and adjudication tasks have a higher per-task rate.

• $50 one-time onboarding reward, paid once your first task on the project is approved.
• Quality incentives: additional earnings for high-quality approved tasks, on terms set out in the project guidelines.