Nuclear Safeguards Red-Teaming Specialist

Neon; United States; Remote; USD 60,000 - 90,000; 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 prompts at three levels, evaluate model responses against policy standards, and craft reference answers with the rationale, drawing on safeguards, material accountancy, and nonproliferation concepts.

Qualifications

• Strong written communication to explain judgments to non-specialists.
• Background in safeguards, nonproliferation, or related regulatory areas.
• Proven experience in drafting prompts and evaluative rubrics.

Responsibilities

• Write prompts across benign, dual-use, and adversarial levels.
• Evaluate model outputs against a defined policy standard.
• Create reference answers with technical rationales.

Skills

Nuclear domain expertise

Red-teaming experience

Technical writing

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 prompts at three levels, evaluate model responses against policy standards, and craft reference answers with the rationale, drawing on safeguards, material accountancy, and nonproliferation concepts.