محلل ضمانات / مفتش لدى الوكالة الدولية للطاقة الذرية أو يوراتوم

About the work

Mercor is assembling a panel of nuclear materials and safeguards 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 material-balance calculation that closes an inspector's account can be used to hide what is missing from it; the same fuel-cycle step that supplies a power reactor is the one a proliferation pathway runs through. A model that refuses a routine accountancy 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 verified nuclear material rather than read about it, inspection regimes, accountancy, and the judgment calls that come with an unresolved discrepancy. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same material-balance figure that closes an account can be used to conceal a diversion. 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):

• IAEA, Euratom or state-system (SSAC/RSAC) inspector, inspection planning, verification, reporting
• Material accountancy, facility declarations, inventory change reports, MUF evaluation and resolution
• Additional Protocol implementation, declarations, complementary access, information analysis
• Safeguards instrumentation and containment/surveillance, NDA measurement, seals, unattended monitoring
• Safeguards-by-design work or safeguards policy analysis at a laboratory, regulator or ministry

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.