AI Radiology Evaluation Expert (Radiologist) – Frontier AI Model Training

We're working with a leading AI research lab to build rigorous evaluations of how well AI reads real radiology studies. The focus is on defining what 'correct' means clinically—ensuring AI gets the load-bearing calls right, such as measurements by the correct convention, interval changes against prior studies, and structured categorization in borderline cases. This is not image labeling but capturing the expert reasoning radiologists perform daily to create reference standards for training and testing frontier AI models.

Requirements

What you'd do:

• Read de-identified studies (CT, MR, radiography, ultrasound, PET/CT, mammography, and more) and write the reference report or specific finding.
• Apply structured systems and measurement conventions you use in practice, such as RECIST, Lung-RADS, BI-RADS, CAD-RADS, ASPECTS, and others.
• Review AI-drafted reads and mark inaccuracies, unsupported claims, or unsafe conclusions.
• Contribute cases that challenge even strong AI models.

Who we're looking for:

• Board-certified or board-eligible radiologists (e.g., ABR, FRCR, EDiR, or international equivalents). Residents and fellows in later training may also be considered.
• Any diagnostic sub-specialty, including neuro, chest, abdominal, MSK, breast, cardiac, nuclear medicine, pediatric, and others.
• Currently reading studies or recently in active practice.

We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.