Clinical AI Benchmark Architect

Weekday AI (YC W21); California City (CA); Hybrid; USD 96,000 - 152,000; Full time

Job summary

Weekday AI is seeking a Clinical Medicine Domain Expert to shape AI-driven clinical reasoning benchmarks. This full-time, 40-hour-per-week role is based in the Bay Area, with hybrid on-site collaboration.

You will evaluate AI outputs, define reference solutions, and craft rigorous clinical tasks spanning internal medicine, oncology, radiology, and more. The ideal candidate is an experienced clinician with MD/DO, US licensure, board certification, and a track record of clinical leadership.

Qualifications

• MD/DO from an accredited medical school with residency completion.
• Active and unrestricted medical license in at least one U.S. state.
• Board certification in the candidate's primary medical specialty.

Responsibilities

• Review and assess clinical knowledge tasks and AI outputs for accuracy, safety, and relevance.
• Identify missing reasoning steps, unsafe recommendations, and deviations from guidelines.
• Develop clear instruction specifications and high-quality reference solutions.

Skills

Clinical decision making

AI evaluation

Data quality

Benchmark design

Clinical feedback

Cross-functional collaboration

Education

MD/DO with residency

Medical licensure in US

Board Certification in primary specialty

Tools

AI tools

Research software

Job description

Weekday AI is seeking a Clinical Medicine Domain Expert to shape AI-driven clinical reasoning benchmarks. This full-time, 40-hour-per-week role is based in the Bay Area, with hybrid on-site collaboration.

You will evaluate AI outputs, define reference solutions, and craft rigorous clinical tasks spanning internal medicine, oncology, radiology, and more. The ideal candidate is an experienced clinician with MD/DO, US licensure, board certification, and a track record of clinical leadership.