Radiologicals Safety for Redteaming

About this role

**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 while 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 held responsibility for radioactive material, not just worked near it; source custody, licensing, or the security and response side. 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, They will be writing prompts that sit exactly on that line, then judging whether the model held it. Examples of relevant backgrounds (Ideally w/Red-teaming experience): Radiation Safety Officer (broad-scope licensee) — holds the licence of record; acquisition, inventory, transfer and disposal. Health Physicist (DOE site or national lab) — survey, assay, contamination control and dose planning in high-hazard facilities. Source Security / Vulnerability Assessment Specialist — has assessed how Category 1 and 2 sources get stolen, shielded or moved.