AI Safety Red Teamer (Remote) - Frontier Model Testing

Pubblicato il 17-11-2026 · Mercor · Roma

Mercor is hiring an AI Safety Red Teamer on a contract basis. The role is remote, offering hourly compensation.
You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and assess model robustness across sensitive domains. You will collaborate with AI researchers to improve alignment, robustness, and safety, contributing to red-teaming reports and safety benchmarks.

#J-18808-Ljbffr
Max. 8 MB. Formati Accettati: PDF, RTF, DOC, DOCX, ODT.