Mercor seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.
Scopra di più sui compiti quotidiani, le responsabilità generali e l'esperienza richiesta per questa possibilità scorrendo subito verso il basso.
You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk topics. xysqume
Responsibilities include crafting adversarial prompts, detecting jailbreaks and policy failures, and documenting vulnerabilities to support safety benchmarking and red-teaming reports.
#J-18808-Ljbffr
📌 Adversarial AI Safety Architect for Frontier Models (Roma)
🏢 Mercor
📍 Roma