Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.
¿Tiene lo que se necesita para triunfar? La siguiente información debe ser leída atentamente por todos los candidatos.
You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk, ambiguous topics such as misinformation, cyber, biosecurity, and policy.
Collaborate with AI researchers to improve alignment, robustness, and safety; xqbhyrx document vulnerabilities; and contribute to safety benchmarking and red-teaming reports to shape the next
#J-18808-Ljbffr
📌 Frontier AI Safety Red Teamer (Madrid)
🏢 Mercor
📍 Madrid