Emergency Medicine Physician - AI Evaluation

Braintrust; United States; Remote; USD 153,000 - 219,000; Part time

Job summary

Turing is seeking a physician with emergency medicine expertise to develop and evaluate AI-driven clinical scenarios. You will craft realistic cases, assess model responses and help define clinically defensible standards within your specialty.

Responsibilities include creating longitudinal tasks, evaluating records and ensuring high-quality, safe content. The role is remote, part-time to start, for a 12-week engagement, with overlap with Pacific time.

Qualifications

• 8+ years of relevant professional experience, current or within last 3 years.
• Active physician license, board certification for emergency medicine.
• Relevant healthcare degree or equivalent experience.

Responsibilities

• Create challenging clinical tasks and evaluation rubrics focused on emergency decision-making.
• Synthesize records, identify contradictions and assess patient safety.
• Apply structured rubrics and calibrate cases through cycles.
• Review and calibrate contributors' work to maintain quality standards.

Skills

Emergency medicine expertise

Clinical reasoning

Written communication

Rubric-based review

Education

Medical license

Board certification in Emergency Medicine

Healthcare degree or equivalent experience

Tools

AI evaluation

Quality improvement

Job description

• Rate: $135/hr


• Hours: 20 hours / week


• Experience: 5 - 10 years


• Location: Alabama, USA | Alaska, USA + 49 more

Bring your emergency medicine physician expertise to the development and evaluation of advanced AI systems. You will create realistic clinical cases, evaluate model responses and help establish clinically defensible standards within your specialty.

What You Will Do

Create challenging clinical tasks, longitudinal-chart scenarios, reference answers and evaluation rubrics focused on emergency clinical decision-making, patient safety and emergency-care or EMS handoffs.

Synthesize fragmented records, identify contradictions and missing actions, and assess clinical reasoning, documentation quality and patient safety.

Apply structured rubrics, review specialist feedback and refine cases through calibration cycles.

Review and calibrate contributors' work, resolve ambiguous clinical or rubric issues and help maintain consistent quality standards.

What You Bring

At least 8 years of relevant professional experience, with current practice or recent practice within the last three years.

An active physician license, board certification or recognized credential appropriate to emergency medicine.

A relevant healthcare degree or equivalent practical experience.

Strong clinical reasoning, chart-review, documentation and written communication skills, with attention to clinically defensible conclusions and patient safety.

Ability to follow standardized rubrics, incorporate critique and work through fast-paced review and calibration cycles.

Nice to Have

Familiarity with US clinical guidelines, payer policies, regulatory requirements and healthcare workflows.

Experience with AI evaluation, clinical content or assessment development, expert review or quality improvement.

Engagement

Remote contractor project for US-based professionals, expected to last 12 weeks. Target start: November 2, 2026.

Part-time (20 hours per week) or full-time (40 hours per week), with four hours of overlap with Pacific working hours.

Selection includes an application review and assessment.

Compensation

USD 135 per hour.

Company: Turing