AI Red-Teamer — Adversarial Testing at Mercor

AI Red-Teamer — Adversarial Testing | $50.5/hr | Remote (US & South Korea) | English & Korean Required

Join Mercor's specialized red team to probe AI systems, uncover vulnerabilities, and generate critical safety data that makes AI more secure and trustworthy for our customers.

Why This Role Matters

At Mercor, we believe the safest AI is one that's already been attacked — by us. As an AI Red-Teamer, you'll be part of an elite team of human data experts who test conversational AI models with adversarial inputs, surface hidden vulnerabilities, and create the datasets that strengthen AI safety.

Note: This project involves reviewing AI outputs on sensitive topics including bias, misinformation, and harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional with clear guidelines and wellness resources provided.

What You'll Do

• Conduct adversarial testing on conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
• Apply structured methodologies using taxonomies, benchmarks, and playbooks to ensure consistent testing
• Document findings reproducibly through detailed reports, datasets, and attack cases that customers can act upon

Required Qualifications

• Native-level fluency in both English and Korean
• Prior red teaming experience (AI adversarial work, cybersecurity, or socio-technical probing)
• Curious and adversarial mindset with instinct to push systems to breaking points
• Structured approach using frameworks and benchmarks, not just random testing
• Strong communication skills to explain risks to both technical and non-technical stakeholders
• Adaptability to thrive across multiple 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/disinformation probing, abuse analysis, conversational AI testing
• Creative probing: psychology, acting, or writing for unconventional adversarial thinking

Success Metrics

• Uncover vulnerabilities that automated tests miss
• Deliver reproducible artifacts that strengthen customer AI systems
• Expand evaluation coverage with more scenarios tested and fewer production surprises
• Build customer trust in AI safety through comprehensive adversarial probing

Why Join Mercor

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

Work Type: Full-time or Part-time Contract | Location: Remote (USA and South Korea only)