Mercor is seeking an AI Safety Red Teamer for contract work to stress-test frontier AI models and identify unsafe behaviors.Verifichi che le sue competenze e la sua esperienza corrispondano ai requisiti di questo ruolo, quindi si candidi con il suo CV qui sotto.The role emphasizes documenting vulnerabilities and contributing to red-teaming efforts for safety benchmarking.You 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.
xysqume #J-*****-LjbffrPer questa posizione sono disponibili opzioni di lavoro a distanza/a casa.
📌 Remote Ai Safety Red Teamer - Adversarial Prompting (Lazio)
🏢 Mercor
📍 Lazio