AI Safety & Red Team Expert at Mercor

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

Mercor is assembling a team of adversarial AI specialists to probe, stress-test, and improve the safety of cutting-edge AI models. If you instinctively push systems to their limits and communicate risk with clarity, this role was built for you. Native fluency in both English and Swedish is required.

Why This Role Exists

The safest AI is the one that's already been attacked — by experts like you. As part of Mercor's red team, you'll surface vulnerabilities in AI models before they reach production, generating the adversarial data that makes AI systems more robust and trustworthy for customers worldwide.

Note: This project involves reviewing AI outputs on sensitive topics (bias, misinformation, harmful behaviors). All work is text-based. Participation in higher-sensitivity tasks is 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 ensure consistent and reproducible testing
• Produce detailed reports, datasets, and attack case documentation that customers can act on

Who You Are

• Experienced in red teaming — AI adversarial work, cybersecurity, or socio-technical probing
• Naturally curious and adversarial — you instinctively find breaking points in systems
• Structured in your approach — you use frameworks, not just random hacks
• A clear communicator — able to explain risks to both technical and non-technical stakeholders
• Adaptable — comfortable moving across diverse projects and customer environments

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 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 at scale