Nuclear Safeguards Inspector & AI Red-Team Auditor

Mercor; United States; Remote; USD 90,000 - 150,000; Full time

Job summary

Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The role focuses on writing prompts at three levels—benign, dual-use, and adversarial—and evaluating model responses for policy compliance.

You will provide a reference answer and technical reasoning to guide safe handling of sensitive topics. We seek candidates with verified nuclear material knowledge and strong technical writing skills, capable of clearly articulating judgments for

Responsibilities

• Write challenging single-turn prompts in your domain, labelled across three levels: benign, dual-use, and adversarial.
• Evaluate model responses against a defined policy standard and judge whether each was handled correctly.

Job description

Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The role focuses on writing prompts at three levels—benign, dual-use, and adversarial—and evaluating model responses for policy compliance.

You will provide a reference answer and technical reasoning to guide safe handling of sensitive topics. We seek candidates with verified nuclear material knowledge and strong technical writing skills, capable of clearly articulating judgments for