Frontier AI Safety Red Team Lead

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/7hmkwx

Obsidian seeks experienced AI Safety Red Teamers to stress-test frontier AI models with adversarial prompts, identifying jailbreaks and unsafe outputs. You will evaluate performance across high-risk topics and document vulnerabilities for benchmarking reports.
Join a team collaborating with AI researchers to improve alignment, robustness, and safety, while delivering practical insights from real-world scenarios in Rome and beyond.

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/7hmkwx