Nuclear Safeguards Red-Team Expert

Mercor; New York (NY); On-site; USD 120,000 - 170,000; Full time

Job summary

Mercor is assembling a panel of nuclear domain experts to red-team frontier AI models. The task is to craft challenging prompts across benign, dual-use, and adversarial levels, and to evaluate model responses against a policy standard.

You will write reference answers and the technical reasoning behind them. This is a writing-intensive role requiring safeguards experience and the ability to explain complex judgments to non-specialists.

Qualifications

• Background in safeguards, nonproliferation, or related policy analysis.
• Experience writing technical material for non-specialist audiences.
• Strong ability to justify judgments with clear written rationale.

Responsibilities

• Write challenging single-turn prompts across three levels: benign, dual-use, and adversarial.
• Evaluate model responses against a defined policy standard.
• Draft reference answers and technical rationale explaining why responses are acceptable or not.

Skills

Red-teaming prompts

Technical writing

Policy evaluation

Nuclear domain knowledge

Education

Nuclear engineering background

Job description

Mercor is assembling a panel of nuclear domain experts to red-team frontier AI models. The task is to craft challenging prompts across benign, dual-use, and adversarial levels, and to evaluate model responses against a policy standard.

You will write reference answers and the technical reasoning behind them. This is a writing-intensive role requiring safeguards experience and the ability to explain complex judgments to non-specialists.