Remote AI Safety Red Team Expert for Frontier Models

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/7hkduf

Mercor seeks an AI Safety Red Teamer to stress-test frontier AI models by designing adversarial prompts and identifying jailbreaks, unsafe behaviors, and policy failures. The role covers evaluating model robustness across misinformation, cyber, biosecurity, fraud, politics, and other sensitive domains.
Responsibilities include documenting vulnerabilities and contributing to safety benchmarking, while collaborating with AI researchers to improve alignment, robustness, and safety in a fully remote

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/7hkduf