Nuclear Security Red Team - AI Safety Evaluator

Mercor; San Francisco (CA); On-site; USD 120,000 - 170,000; Full time

Job summary

Mercor in San Francisco is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. You will write challenging prompts across benign, dual-use, and adversarial levels, and evaluate model responses against a defined policy standard.

This writing-intensive role demands clear, written rationales for every judgment. Prior technical writing, published research, or expert witness experience is a strong signal; please include a sample or link with your application.

Qualifications

• Backgrounds in material control and accountability (MC&A) programme design, operation or assessment at a national laboratory or licensee.
• Physical protection system engineering—sensors, barriers, delay, response force, performance testing.
• Vulnerability assessment and adversary path analysis for nuclear facilities.
• Insider threat and human reliability programme work.
• Nuclear security policy, training or international assistance programmes.

Responsibilities

• 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.

Skills

MC&A design

Physical protection systems

Vulnerability assessment

Insider threat

Nuclear security policy

Job description

Mercor in San Francisco is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. You will write challenging prompts across benign, dual-use, and adversarial levels, and evaluate model responses against a defined policy standard.

This writing-intensive role demands clear, written rationales for every judgment. Prior technical writing, published research, or expert witness experience is a strong signal; please include a sample or link with your application.