Nuclear Security Red Team — Prompt Engineer

Obsidian; San Francisco (CA); On-site; USD 110,000 - 190,000; 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.

This role requires writing prompts across three levels and evaluating responses against a policy standard, followed by creating the reference answer with clear technical reasoning for non‑specialists.

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.

This role requires writing prompts across three levels and evaluating responses against a policy standard, followed by creating the reference answer with clear technical reasoning for non‑specialists.