Une candidature sur mesure pour ce poste — un CV personnalisé et une lettre de motivation qui correspondent directement à l’offre.
Mercor is assembling a panel of propulsion and initiation experts to red-team frontier AI models. The goal is to test whether a model can correctly judge misuse potential, answering legitimate questions fully while refusing genuinely dangerous ones.
You will work in a highly technical, writing-intensive environment. Responsibilities include writing challenging single-turn prompts in benign, dual-use, and adversarial categories; evaluating model outputs against a defined policy standard; and
Mercor is assembling a panel of propulsion and initiation experts to red-team frontier AI models. The goal is to test whether a model can correctly judge misuse potential, answering legitimate questions fully while refusing genuinely dangerous ones.
You will work in a highly technical, writing-intensive environment. Responsibilities include writing challenging single-turn prompts in benign, dual-use, and adversarial categories; evaluating model outputs against a defined policy standard; and