AI Safety & Red Team Expert at Mercor

AI Safety & Red Team Expert | $48–62/hr | Worldwide Remote | English & Norwegian Required

Mercor is building a frontier red team of human data experts who probe AI models for vulnerabilities before bad actors do. If you think adversarially, work with structure, and want to make AI systems genuinely safer, this role is for you. Native fluency in both English and Norwegian is required.

Why This Role Exists

The safest AI is the one that's already been stress-tested. Mercor assembles expert red teamers who surface vulnerabilities, generate adversarial datasets, and deliver reproducible findings that help customers trust their AI systems. This is text-based work; participation in higher-sensitivity projects is always optional and supported by clear guidelines and wellness resources.

What You'll Do

• Red team conversational AI models and agents — jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structured frameworks, taxonomies, and benchmarks to keep testing consistent and reproducible
• Produce clear reports, datasets, and attack cases that customers can act on

Who You Are

• Experienced in AI adversarial work, cybersecurity, or socio-technical probing
• Naturally curious and adversarial — you instinctively push systems to their limits
• Structured in your approach — you use frameworks, not just random hacks
• A clear communicator who can explain risks to both technical and non-technical audiences
• Adaptable and comfortable moving across diverse projects and customers

Nice-to-Have Specialties

• Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• Cybersecurity: penetration testing, exploit development, reverse engineering
• Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing
• Creative probing: psychology, acting, or writing applied to unconventional adversarial thinking

What Success Looks Like

• You uncover vulnerabilities that automated tests miss
• You deliver reproducible artifacts that strengthen customer AI systems
• Evaluation coverage expands — more scenarios tested, fewer surprises in production
• Mercor customers trust their AI because you've already probed it like an adversary

Why Join Mercor

• Build hands-on experience in human data-driven AI red teaming at the frontier of safety
• Play a direct role in making AI systems more robust, safe, and trustworthy