Remote AI Safety Red Team Specialist

Mercor; Toronto; Remote; CAD 112,000 - 167,000; Full time

Job summary

Mercor is seeking a remote Red Team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to enhance safety. Work involves reviewing outputs touching sensitive topics and producing reproducible artifacts for customers.

You will apply structured frameworks, document attack scenarios, and collaborate with stakeholders to ensure robust AI safety across projects and clients.

Qualifications

• Red team experience in AI adversarial work or cybersecurity.
• You use frameworks or benchmarks, not just random hacks.
• You can explain risks clearly to technical and non-technical stakeholders.
• You generate high-quality human data and annotate failures.

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

Adversarial AI

Cybersecurity

Structured testing

Communication

Adaptability

Job description

Mercor is seeking a remote Red Team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data to enhance safety. Work involves reviewing outputs touching sensitive topics and producing reproducible artifacts for customers.

You will apply structured frameworks, document attack scenarios, and collaborate with stakeholders to ensure robust AI safety across projects and clients.