AI Safety & Red Team Expert at Mercor

AI Safety & Red Team Expert (English & Danish) | $48–62/hr | Worldwide Remote

Mercor is building a frontier red team of human data experts who probe AI models for vulnerabilities, surface adversarial risks, and generate the safety data that makes AI systems more trustworthy. Native fluency in both English and Danish is required. This is a contractor role with flexible, hourly engagement.

Why This Role Exists

The safest AI is one that's already been stress-tested by skilled adversaries. Mercor assembles expert red teamers to attack AI models before bad actors do — uncovering jailbreaks, bias exploits, and systemic risks that automated tests miss. All work is text-based, and any higher-sensitivity projects are clearly communicated in advance, with optional participation and wellness resources provided.

What You'll Do

• Red team conversational AI models and agents — including 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 ensure consistent and reproducible testing
• Produce clear reports, datasets, and attack case documentation that customers can act on

Who You Are

• You have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
• You instinctively push systems to their breaking points with curiosity and structure
• You use established frameworks — not just random hacks — to guide your testing approach
• You communicate risks clearly to both technical and non-technical stakeholders
• You thrive in dynamic environments, moving fluidly across 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 skills applied to unconventional adversarial thinking

What Success Looks Like

• You uncover vulnerabilities that automated tests miss
• You deliver reproducible artifacts that directly 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 AI safety
• Play a direct role in making AI systems more robust, safe, and trustworthy for real-world deployment