Frontier AI Safety Red Team Specialist

Mercor seeks experienced AI Safety Red Teamers to stress-test frontier AI models by designing adversarial prompts and evaluating robustness across complex, high-risk topics. You will identify jailbreaks, unsafe behaviours, hallucinations, and policy failures while documenting vulnerabilities for benchmarking and reporting.Collaboration with AI researchers...

Mercor is seeking a remote-friendly red team data specialist to test conversational AI models, identify vulnerabilities, and generate actionable data. You will document findings, follow structured playbooks, and work across projects with diverse clients.Fluent in English and Danish, you will convey risks clearly to both technical and non-technical...

Obsidian seeks experienced AI Safety Practitioners to evaluate the safety, quality, and alignment of frontier AI models across complex, policy-sensitive topics. You will assess AI-generated responses, apply safety policies, and help improve model behavior through structured evaluations and feedback.Responsibilities include evaluating outputs for safety,...

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing, prompt design, and rigorous evaluation of model behavior in high-risk contexts.You will collaborate with AI researchers to stress-test models, document weaknesses, and contribute to safety benchmarking across misinformation,...

Mercor seeks experienced AI Safety Practitioners to evaluate safety, quality, and alignment of frontier AI models across sensitive, policy-driven topics. You will assess AI-generated responses, apply safety policies, and contribute to improving model behavior through structured evaluations and feedback.Responsibilities include evaluating outputs for safety...

Mercor is seeking a remote AI red-teaming specialist to probe conversational models, expose vulnerabilities, and produce actionable data. You will follow structured methodologies to ensure repeatable, high‑quality results across diverse projects.The role emphasizes clear risk communication and adaptability across multiple customers and engagements. Success...

We 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...

Mercor is seeking experienced AI Safety Practitioners to evaluate safety, quality and alignment of frontier AI models on complex topics. You will assess AI-generated responses, apply safety policies, and help improve model behaviour through structured evaluations and feedback.Responsibilities include evaluating safety and accuracy, reviewing sensitive...

Obsidian is seeking experienced AI Safety Practitioners to evaluate safety, quality, and alignment of frontier AI models across complex, policy-sensitive topics. You will assess AI-generated responses, apply safety policies, and help improve model behavior through structured evaluations and feedback.Join a team that reviews content involving misinformation,...