Artificial Intelligence Specialist
AI Safety Red Teamer [$70-$84/hr]
Experienced AI Safety Red Teamers to design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous ("grey-area") topics
Role Responsibilities
Design adversarial prompts to stress-test frontier AI modelsIdentify jailbreaks, unsafe behaviours, hallucinations, and policy failuresEvaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domainsDocument vulnerabilities and contribute to safety benchmarking and red-teaming reportsCollaborate with AI researchers to improve model alignment, robustness, and safety
Good Candidature
Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related fieldStrong analytical reasoning, prompt design, and written communication skillsExperience designing adversarial prompts or evaluating frontier AI systems
Nice to Have
Experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & SafetyFamiliarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologiesExpertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety