Remote AI Safety Red Team Specialist

Mercor; New York (NY); On-site; USD 120,000 - 180,000; Full time

Job summary

Mercor is assembling a remote red team to test large language models and AI agents by probing for jailbreaks, prompt injections, and systemic risks. You will work with English and Vietnamese inputs to surface vulnerabilities and produce actionable data for customers.

You bring prior red-teaming or cybersecurity experience, a structured mindset, and strong communication skills to explain risks to technical and non-technical stakeholders.

Qualifications

• Red teaming experience in AI adversarial work, cybersecurity or socio-technical probing.
• Curious and adversarial; you push systems to breaking points.
• Structured; you use frameworks or benchmarks, not random hacks.
• Communicative; you explain risks clearly to technical and non-technical stakeholders.
• Adaptable; you thrive across projects and customers.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation
• 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

Skills

Red teaming

AI adversarial work

Cybersecurity

Socio-technical probing

Communication

Adaptability

Job description

Mercor is assembling a remote red team to test large language models and AI agents by probing for jailbreaks, prompt injections, and systemic risks. You will work with English and Vietnamese inputs to surface vulnerabilities and produce actionable data for customers.

You bring prior red-teaming or cybersecurity experience, a structured mindset, and strong communication skills to explain risks to technical and non-technical stakeholders.