AI Red-Teamer — Adversarial AI Testing; English

Location: Remote-friendly (US time zones); Geography restricted to US, UK, Canada Type: Full-time or Part-time

At Mercor, we believe the safest AI is the one that’s already been attacked — by us. That’s why we’re building a pod of AI Red-Teamers: 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.

Location

Type

Why This Role Exists

What You’ll Do

Who You Are

Nice-to-Have Specialties

What Success Looks Like

Why Join Mercor

Location: Remote-friendly (US time zones); Geography restricted to US, UK, Canada Type: Full-time or Part-time At Mercor, we believe the safest AI is the one that’s already been attacked — by us. That’s why we’re building a pod of AI Red-Teamers: 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. This role may include 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. Red-team AI models and agents: jailbreaks, prompt injections, misuse cases, exploits Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent Document reproducibly: produce reports, datasets, and attack cases customers can act on Flex across projects: support different customers, from LLM jailbreaks to socio-technical abuse testing You bring prior red-teaming experience (AI adversarial work, cybersecurity, socio-technical probing) You’re curious and adversarial: you instinctively push systems to breaking points You’re structured: you use frameworks or benchmarks, not just random hacks You’re communicative: you explain risks clearly to technical and non-technical stakeholders You’re adaptable: thrive on moving across projects and customers 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 Creative probing: psychology, acting, writing for unconventional adversarial thinking You uncover vulnerabilities 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 the safety of their AI because you’ve already probed it like an adversary Build experience in human data-driven AI red-teaming at the frontier of safety Play a direct role in making AI systems more robust, safe, and trustworthy The pay rate for this role may vary by project, customer, and content category. Compensation will be aligned with the level of expertise required, the sensitivity of the material, and the scope of work for each engagement. We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.

• Red-team AI models and agents: jailbreaks, prompt injections, misuse cases, exploits
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent Document reproducibly: produce reports, datasets, and attack cases customers can act on
• Flex across projects: support different customers, from LLM jailbreaks to socio-technical abuse testing
• You bring prior red-teaming experience (AI adversarial work, cybersecurity, socio-technical probing)
• You’re curious and adversarial: you instinctively push systems to breaking points
• You’re structured: you use frameworks or benchmarks, not just random hacks
• You’re communicative: you explain risks clearly to technical and non-technical stakeholders
• You’re adaptable: thrive on moving across projects and customers
• 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
• Creative probing: psychology, acting, writing for unconventional adversarial thinking
• You uncover vulnerabilities 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 the safety of their AI because you’ve already probed it like an adversary
• Build experience in human data-driven AI red-teaming at the frontier of safety
• Play a direct role in making AI systems more robust, safe, and trustworthy