Proliferation & AI Safety Red Team Analyst

Obsidian; Paris; Sur place; EUR 70 000 - 100 000; Plein temps

Résumé du poste

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 at three levels (benign, dual-use, and adversarial), evaluate the responses, and draft the reference answer with the technical reasoning.

Qualifications

• This is writing‑intensive work requiring clear written rationale.
• Background in proliferation questions or export controls is preferred.
• Experience reading and writing about misuse scenarios in your field.

Responsabilités

• 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.

Description du poste

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 at three levels (benign, dual-use, and adversarial), evaluate the responses, and draft the reference answer with the technical reasoning.