Nuclear Safeguards Red-Team Researcher

Obsidian; San Francisco (CA); On-site; USD 90,000 - 150,000; Full time

Job summary

Mercor is assembling a panel of nuclear domain 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 across benign, dual-use, and adversarial levels; evaluate responses against a policy standard; and draft reference answers with the technical reasoning for why.

Qualifications

• Experience in nuclear safeguards, fuel cycle, or nonproliferation contexts.
• Strong ability to articulate reasoning for non-specialists.
• Experience with red-teaming or policy evaluation is a plus.

Responsibilities

• Write challenging prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a policy standard and judge correctness.
• Draft reference answers with technical reasoning for correct responses.

Skills

Prompt writing

Technical writing

Nuclear safeguards knowledge

Education

Background in safeguards/IAEA or nonproliferation

Job description

Mercor is assembling a panel of nuclear domain 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 across benign, dual-use, and adversarial levels; evaluate responses against a policy standard; and draft reference answers with the technical reasoning for why.