AI Safety Red Teamer

The role of an AI Safety Red Teamer involves identifying and addressing vulnerabilities in advanced AI systems through adversarial testing. The company focuses on developing and securing frontier AI models, ensuring they are robust and safe across various high-risk domains. The main day-to-day responsibilities include designing adversarial prompts to test AI models, identifying issues like jailbreaks, unsafe behaviors, and policy failures, and evaluating the robustness of models in areas such as misinformation, cybersecurity, and biosecurity. The role also involves documenting vulnerabilities and contributing to safety benchmarking and red-teaming reports, as well as collaborating with AI researchers to enhance model alignment and safety. To qualify, candidates must have a Bachelor's degree or higher in fields such as Computer Science, Cybersecurity, or related disciplines, along with 5+ years of professional experience in AI Safety, AI Red Teaming, or similar fields. Strong analytical reasoning, prompt design, and written communication skills are essential. Nice-to-have skills include experience with AI Red Teaming methodologies, familiarity with jailbreak testing, and expertise in grey-area domains. What the role asks for: - Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline. - 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field. - Strong analytical reasoning, prompt design, and written communication skills. - Experience designing adversarial prompts or evaluating frontier AI systems.