AI Red-Teamer — Adversarial Testing Specialist at Mercor

AI Red-Teamer — Adversarial Testing | $50.5/hr | Remote (US & Japan) | English & Japanese Fluency Required

Mercor is assembling an elite red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate critical safety data. We believe the safest AI is one that's already been attacked — by us. Join our mission to make AI systems more robust and trustworthy through expert human-driven testing.

What You'll Do

• Red team conversational AI models and agents: execute jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation attacks
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structured methodologies: follow taxonomies, benchmarks, and playbooks to ensure consistent testing
• Document reproducibly: produce detailed reports, datasets, and attack cases that customers can act on

Who You Are

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
• Naturally curious and adversarial: you instinctively push systems to their breaking points
• Structured thinker: you use frameworks and benchmarks, not just random hacks
• Strong communicator: you explain risks clearly to both technical and non-technical stakeholders
• Adaptable: you thrive on moving across diverse projects and customers
• Native-level fluency in both English and Japanese is required

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 for 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 safety because you've already probed it like an adversary

Important Note

This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources. Topics will be clearly communicated before exposure to any content.

Why Join Mercor

• Build frontier experience in human data-driven AI red teaming at the cutting edge of AI safety
• Play a direct role in making AI systems more robust, safe, and trustworthy
• Work remotely with flexible full-time or part-time contract arrangements