Nuclear Safeguards Specialist - Fully Remote

Mercor; New York (NY); Remote; USD 110,000 - 170,000; Full time

Job summary

Mercor, based in New York, is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The aim is to test whether a model can judge misuse potential while answering legitimate questions fully and refusing genuinely dangerous ones.

You will write prompts across benign, dual-use, and adversarial levels; evaluate model outputs against a policy standard; and craft the reference answer with the reasoning.

Qualifications

• Experience writing prompts and evaluating model responses in security-sensitive contexts.
• Ability to justify judgments with clear, accessible rationale for non-specialists.
• Strong written communication and analytical skills.

Responsibilities

• Write prompts across benign, dual-use, and adversarial levels.
• Evaluate model outputs against a defined policy standard.
• Draft the reference answer and technical reasoning for correct responses.

Skills

Prompts writing

Policy evaluation

Technical writing

Education

Experience in export control or proliferation analysis

Tools

Research methods

Job description

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 control list that stops a shipment tells a procurement agent what to avoid declaring; the same pathway analysis that informs policy is a roadmap read from the other direction. A model that refuses a routine export-classification 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 worked proliferation questions professionally — export control, treaty implementation, or programme analysis — and who can tell a compliance question from a circumvention question. What matters most is being able to tell a routine professional question from one that's fishing for something else: the same control list that blocks a transfer also names what to route around. 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):

• Export control licensing, classification or enforcement — dual-use lists, catch-all controls, end-user screening
• Treaty and agreement implementation — NPT, CTBT, safeguards agreements, bilateral cooperation agreements
• Proliferation pathway and programme analysis at a laboratory, agency, ministry or research institute
• Sanctions, procurement network or illicit trade analysis
• Open-source and technical analysis of nuclear programmes

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.