Remote AI Safety Red Team Specialist

Mercor; Oslo; Remote; NOK 661,000 - 1,039,000; Full time

Job summary

Mercor is seeking a remote Red Team data expert to help assess safety of conversational AI systems. You will probe AI models with adversarial inputs, annotate failures, and generate actionable artifacts to strengthen customer AI safety.

You’ll operate across various projects, applying frameworks and playbooks to ensure consistency, and you will document results in reproducible datasets and reports for clients and stakeholders.

Qualifications

• You bring prior red teaming experience in AI adversarial contexts.
• Ability to annotate vulnerabilities and surface systemic risks.
• Comfort with documenting results using structured taxonomies and playbooks.
• Excellent communication skills to explain risks 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 by annotating failures and classifying vulnerabilities
• 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 experience

AI adversarial work

Cybersecurity

Socio-technical probing

Structured frameworks

Communication

Job description

Mercor is seeking a remote Red Team data expert to help assess safety of conversational AI systems. You will probe AI models with adversarial inputs, annotate failures, and generate actionable artifacts to strengthen customer AI safety.

You’ll operate across various projects, applying frameworks and playbooks to ensure consistency, and you will document results in reproducible datasets and reports for clients and stakeholders.