AI Red-Teamer — Adversarial Testing at Mercor

AI Red-Teamer — Adversarial Testing | $28.74/hr | Remote (US & Brazil) | English & Brazilian Portuguese Required

Join Mercor's elite red team to probe AI systems for vulnerabilities and generate critical safety data. This role requires native-level fluency in both English and Brazilian Portuguese, offering flexible full-time or part-time contract work.

Why This Role Exists

At Mercor, we believe the safest AI is the one that's already been attacked — by us. We're assembling a specialized red team of human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers.

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.

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 methodologies: follow taxonomies, benchmarks, and playbooks to ensure consistent testing
• Document reproducibly: produce reports, datasets, and attack cases that customers can act on

Who You Are

• Prior red teaming experience (AI adversarial work, cybersecurity, or socio-technical probing)
• Curious and adversarial mindset: you instinctively push systems to breaking points
• Structured approach: you use frameworks or benchmarks, not just random hacks
• Strong communicator: you explain risks clearly to technical and non-technical stakeholders
• Adaptable: thrive on moving across projects and customers
• Native-level fluency in both English and Brazilian Portuguese

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

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

Why Join Mercor

• Build frontier experience in human data-driven AI red teaming
• Play a direct role in making AI systems more robust, safe, and trustworthy
• Competitive compensation aligned with expertise and scope of work