Remote AI Red Team Engineer

Mercor; New York (NY); Remote; USD 90,000 - 160,000; Full time

Job summary

Mercor is assembling a red team for this project—human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to make AI safer for customers. This role centers on reviewing outputs touching on bias, misinformation, or harmful behaviors, with topics clearly communicated before exposure and wellness resources available.

You’ll tackle jailbreaks, prompt injections, misuse cases and multi-turn manipulation, generate high-quality labeled data,

Qualifications

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Curious and adversarial: you instinctively push systems to breaking points.
• Structured: you use frameworks or benchmarks, not just random hacks.
• Communicative: you explain risks clearly to technical and non-technical stakeholders.
• Adaptable: thrive on moving 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 team experience

Curious/adversarial mindset

Structured approach

Communication skills

Adaptability

Job description

Mercor is assembling a red team for this project—human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to make AI safer for customers. This role centers on reviewing outputs touching on bias, misinformation, or harmful behaviors, with topics clearly communicated before exposure and wellness resources available.

You’ll tackle jailbreaks, prompt injections, misuse cases and multi-turn manipulation, generate high-quality labeled data,