Une candidature sur mesure pour ce poste — un CV personnalisé et une lettre de motivation qui correspondent directement à l’offre.
Mercor in Paris is assembling a panel of nuclear domain experts to red-team frontier AI models, testing the ability to judge misuse while providing legitimate information. You will write prompts across benign, dual-use, and adversarial categories, and evaluate responses against a policy standard.
The role emphasizes thorough written rationales and reference answers, with prior writing and safeguards experience being a strong signal.
Mercor in Paris is assembling a panel of nuclear domain experts to red-team frontier AI models, testing the ability to judge misuse while providing legitimate information. You will write prompts across benign, dual-use, and adversarial categories, and evaluate responses against a policy standard.
The role emphasizes thorough written rationales and reference answers, with prior writing and safeguards experience being a strong signal.