فيزيائي صحي

About the work

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request, answering legitimate questions fully while refusing genuinely dangerous ones.

You will:

• Write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
• Evaluate the responses that come back against a defined policy standard, and judge whether each was handled correctly.
• Write the reference answer, what a correct response looks like, and the technical reasoning for why.

This domain lives on the dual-use line more than most. The same isotope underpins cancer therapy and industrial radiography; the same shielding calculation protects a worker and conceals a source. A model that refuses a routine dose question is failing as badly as one that answers a question it shouldn't. Drawing that line reliably is why we need practitioners rather than generalists.

Background we're looking for

We're looking for people who have done the measurement and the dose planning themselves, in a facility where getting it wrong mattered, survey, assay, contamination control, work planning. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same shielding calculation protects a worker and conceals a source. You will be writing prompts that sit exactly on that line, then judging whether the model held it.

Examples of relevant backgrounds (ideally with red-teaming experience):

• Operational health physicist at a DOE site, national laboratory or reactor facility, survey, assay, contamination control
• Internal dosimetry or bioassay specialist, intake assessment, dose reconstruction, committed dose
• Decommissioning and D&D health physicist, characterisation surveys, MARSSIM, release criteria
• Accelerator or reactor health physics, activation products, neutron fields, shielding design and verification
• Dose planning for high-hazard work, RWP development, ALARA reviews, hot-cell and glovebox operations

What this role demands beyond technical depth

This is writing-intensive work. Every judgment you make needs a written rationale that a non-specialist can follow. Prior technical writing, published research, or expert witness experience is a strong signal; please include a sample or link. You will also be reading and writing about misuse scenarios in your field for sustained periods. We brief experts on this in advance, and you can pause or step away at any point without penalty.

Before you apply

Your work here will not involve, and must not draw on, classified or export-controlled information, or anything covered by an NDA or prepublication review obligation. If you hold such obligations you may still be a good fit; tell us in your application and we will scope the work accordingly.