Mercor is seeking an AI Safety Red Teamer for a remote contract to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, and policy failures. You will evaluate model robustness across cyber, biosecurity, misinformation, fraud, and political content, documenting vulnerabilities for benchmarking and reports.The role requires a strong background in AI safety, red teaming, or related fields, with proven experience in adversarial prompt design and rigorous written communication #J-18808-Ljbffr
📌 Remote AI Safety Red Teamer — Contract (Milano)
🏢 Mercor
📍 Milano