Mercor is seeking an AI Safety Red Teamer to design adversarial prompts and stress-test frontier AI models in a fully remote contract role. You will identify jailbreaks, unsafe behaviors, hallucinations, and policy failures while evaluating model robustness across diverse sensitive domains. Collaborate with researchers to improve alignment and safety. Required: a Bachelor's degree or higher in a related field and 5+ years of experience in AI Safety, red-teaming, or safety-focused roles, with
📌 Remote AI Safety Red Teamer — Adversarial Prompting (España)
🏢 Mercor
📍 España