pMercor is seeking an AI Safety Red Teamer for contract work to stress-test frontier AI models and identify unsafe behaviors. The role emphasizes documenting vulnerabilities and contributing to red-teaming efforts for safety benchmarking. /ppYou will design adversarial prompts, evaluate model robustness, and collaborate with AI researchers to improve alignment across diverse, sensitive domains. Remote contract with competitive hourly compensation. /p #J-18808-Ljbffr
📌 Remote AI Safety Red Teamer - Adversarial Prompting (Roma)
🏢 Mercor
📍 Roma
Candidati a questo annuncio
Mostra le tue capacità professionali all'azienda, compila il form e lascia un tocco personale nella lettera di presentazione, aiuterà il recruiter nella scelta del candidato.