Nuclear Safeguards Red-Teaming Expert

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

Job summary

Mercor is assembling a panel of nuclear domain experts to red-team frontier AI models, testing whether a model can judge misuse potential while answering legitimate questions fully and refusing dangerous ones.

You will write prompts at three levels, evaluate model responses, and craft reference answers with reasoning to guide safe, responsible outputs. This is a writing-intensive, analytical role requiring clear explanations.

Qualifications

• Experience in nuclear safeguards or related policy domains.
• Strong technical writing with clear rationale in plain language.
• Background in Safeguards Analyst / IAEA or Euratom Inspector is a strong signal.
• Experience with red-teaming prompts and misuse scenario assessment is preferred.

Responsibilities

• Write challenging single-turn prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a defined policy standard.
• Draft reference answers with technical reasoning for correct and safe replies.
• Provide written rationales that non-specialists can follow.

Job description

Mercor is assembling a panel of nuclear domain experts to red-team frontier AI models, testing whether a model can judge misuse potential while answering legitimate questions fully and refusing dangerous ones.

You will write prompts at three levels, evaluate model responses, and craft reference answers with reasoning to guide safe, responsible outputs. This is a writing-intensive, analytical role requiring clear explanations.