Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.
Scorra la pagina per visualizzare tutti i requisiti del lavoro e le responsabilità che i candidati selezionati dovranno assumersi.
You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous topics.Responsibilities include designing adversarial prompts, identifying jailbreaks and policy failures, evaluating xbvzest robustness across misinformation and sensitive domains, documenting vulnerabilities, and collaborating with AI
📌 Frontier AI Safety Red Team Specialist (Roma)
🏢 Obsidian
📍 Roma