AI Safety Red Team Specialist (Remote)

Obsidian; Oslo; Remote; NOK 855,000 - 1,330,000; Full time

Job summary

Mercor is assembling a red team for AI safety. We’re seeking human data experts to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that strengthens our customers’ AI systems.

You will review model outputs touching sensitive topics, annotate failures, classify vulnerabilities, and document reproducible attack cases with clear guidelines and wellness support. Remote work available, with collaboration across projects.

Qualifications

• Red team experience in AI adversarial work, cybersecurity, or socio-technical probing is required.
• Comfort using frameworks or benchmarks to test systems.
• Strong ability to communicate risks clearly to technical and non-technical stakeholders.

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

AI adversarial work

Cybersecurity

Structured testing

Clear communication

Job description

Mercor is assembling a red team for AI safety. We’re seeking human data experts to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that strengthens our customers’ AI systems.

You will review model outputs touching sensitive topics, annotate failures, classify vulnerabilities, and document reproducible attack cases with clear guidelines and wellness support. Remote work available, with collaboration across projects.