Nuclear Materials AI Red-Team Strategist

Mercor; San Francisco (CA); Remote; USD 120,000 - 180,000; Full time

Job summary

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 prompts, evaluate model outputs, and compose reference answers with detailed technical reasoning. This writing-intensive role emphasizes precise justification and careful risk discernment.

Qualifications

• Experience in nuclear forensics casework or international exercise participation.
• Experience with radiochemical and mass-spectrometric analyses.
• Knowledge of detection and interdiction technology.
• Background in material signature libraries and attribution methodology.
• Experience with pre- or post-detonation forensics research.

Responsibilities

• Write challenging single-turn prompts in your domain, labelled across three levels.
• Evaluate the responses against a defined policy standard and judge handling correctness.
• Write the reference answer with technical reasoning for why the response is correct or not.

Skills

Nuclear forensics

Analytical work

Detection & interdiction tech

Material signature libraries

Forensics research

Job description

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 prompts, evaluate model outputs, and compose reference answers with detailed technical reasoning. This writing-intensive role emphasizes precise justification and careful risk discernment.