Frontier AI Safety Red Teamer - Adversarial Testing Lead

ppWe are seeking experienced strongAI Safety Red Teamers /strong 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. /ph3Responsibilities /h3ullipDesign adversarial prompts to stress-test frontier AI models. /p /lilipIdentify jailbreaks, unsafe behaviours, hallucinations, and policy failures. /p /lilipEvaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. /p /lilipDocument vulnerabilities and contribute to safety benchmarking and red-teaming reports. /p /lilipCollaborate with AI researchers to improve model alignment, robustness, and safety. /p /li /ulh3Required Qualifications /h3ullipBachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline. /p /lilip5+ years of professional experience in AI Safety, AI Red Teaming, Trust Safety, cybersecurity, investigative journalism, life sciences, or a related field. /p /lilipStrong analytical reasoning, prompt design, and written communication skills. /p /lilipExperience designing adversarial prompts or evaluating frontier AI systems. /p /li /ulh3Preferred Qualifications /h3ullipExperience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust Safety. /p /lilipFamiliarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies. /p /lilipExpertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety. /p /li /ulh3Why Join? /h3ullipHelp secure and strengthen the next generation of frontier AI models. /p /lilipWork on cutting-edge adversarial testing alongside leading AI researchers and safety teams. /p /lilipInfluence how AI systems respond to complex, real-world safety challenges. /p /li /ul /p #J-18808-Ljbffr