AI Safety Specialist
Il y a 3 heures
belgium belgium
mercor
Temps plein
Gratuit avec email ou Google
Enregistrez cette offre et organisez votre recherche
Créez un compte gratuit pour enregistrer des offres d'emploi, créer des alertes et revenir à cette liste depuis votre tableau de bord.
Gratuit avec email ou Google
En continuant, vous acceptez nos Conditions d’utilisation & Politique de confidentialité.
pAbout the job Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey . /ppPosition: AI Safety Red Teamer | Type: Contract | Compensation: $70–$84/hour |
Location:
Remote /ph3Role Responsibilities /h3ulliDesign adversarial prompts to stress-test frontier AI models . /liliIdentify jailbreaks, unsafe behaviors, hallucinations, and policy failures. /liliEvaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. /liliDocument vulnerabilities and contribute to safety benchmarking and red-teaming reports. /liliCollaborate with AI researchers to improve model alignment, robustness, and safety. /li /ulh3Qualifications Must-Have /h3ulliBachelor's degree or higher in Computer Science , Cybersecurity , Journalism , Communications , Psychology , Biology , Chemistry , Public Policy , or a related discipline. /lili5+ years of professional experience in AI Safety , AI Red Teaming , Trust Safety , cybersecurity, investigative journalism, life sciences, or a related field. /liliStrong analytical reasoning, prompt design, and written communication skills. /liliExperience designing adversarial prompts or evaluating frontier AI systems . /li /ulh3Preferred /h3ulliExperience with AI Red Teaming , RLHF , SFT , AI Alignment , or Trust Safety . /liliFamiliarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies. /liliExpertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety. /li /ul
Location:
Remote /ph3Role Responsibilities /h3ulliDesign adversarial prompts to stress-test frontier AI models . /liliIdentify jailbreaks, unsafe behaviors, hallucinations, and policy failures. /liliEvaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. /liliDocument vulnerabilities and contribute to safety benchmarking and red-teaming reports. /liliCollaborate with AI researchers to improve model alignment, robustness, and safety. /li /ulh3Qualifications Must-Have /h3ulliBachelor's degree or higher in Computer Science , Cybersecurity , Journalism , Communications , Psychology , Biology , Chemistry , Public Policy , or a related discipline. /lili5+ years of professional experience in AI Safety , AI Red Teaming , Trust Safety , cybersecurity, investigative journalism, life sciences, or a related field. /liliStrong analytical reasoning, prompt design, and written communication skills. /liliExperience designing adversarial prompts or evaluating frontier AI systems . /li /ulh3Preferred /h3ulliExperience with AI Red Teaming , RLHF , SFT , AI Alignment , or Trust Safety . /liliFamiliarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies. /liliExpertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety. /li /ul