Remote AI Safety Red Teamer
Salva questo lavoro e mantieni la tua ricerca organizzata
Crea un account gratuito per salvare lavori, creare avvisi e tornare a questa inserzione dalla tua dashboard.
Continuando accetti i nostri Termini & Informativa sulla privacy.
Mercor is seeking an AI Safety Red Teamer for a remote contract role.
Competenze, Esperienza, Qualifiche: se possiede i requisiti giusti per questa opportunità, si candidi oggi stesso.
You will design adversarial prompts to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.
You will collaborate with AI researchers to improve alignment, robustness, and safety, documenting vulnerabilities and contributing to safety benchmarking.
A strong background in AI safety or red-teaming and a Bachelor's degree are required. xbvzest
#J-18808-Ljbffr
Per questa posizione sono disponibili opzioni di lavoro da remoto/a casa.
-
Frontier AI Safety Red Teamer
11 ore fa
Firenze, Tuscany, Italia Mercor Tempo pienoMercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.Faccia clic su "Candidati" qui sotto per inviare la sua candidatura. Si assicuri che il suo CV sia aggiornato e di aver prima letto le specifiche del lavoro.You will design challenging prompts, uncover model weaknesses, and...
-
AI Safety Specialist
11 ore fa
Firenze, Tuscany, Italia Mercor Tempo pienoWe are seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous ("grey-area") topics.ResponsibilitiesDesign adversarial prompts to stress-test frontier AI...
-
Remote AI Safety Red Teamer
2 giorni fa
firenze, toscana, Italia Mercor Tempo pienoMercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, hallucinations, and policy failures. You will collaborate with AI researchers to improve alignment, robustness, and safety, documenting vulnerabilities and contributing to...
-
Frontier AI Safety Red Teamer
9 ore fa
firenze, toscana, Italia Mercor Tempo pienoMercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics. You will collaborate with researchers to improve model alignment, robustness, and safety, documenting...