Remote AI Safety Red Team Specialist & Adversarial Trainer

mercor; Norway; Remote; NOK 632,000 - 817,000; Part time

Job summary

Mercor is seeking AI Safety Experts — English & Norwegian for a remote contract role. You will test AI models to uncover jailbreaks, prompt injections, misuse cases, and biases across multilingual contexts.

Ideal candidates have prior red-teaming experience in AI adversarial work or cybersecurity, and can apply structured testing using benchmarks. Excellent communication with diverse stakeholders and adaptability to work across multiple projects are essential.

Qualifications

• Fluent in English and Norwegian.
• Prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Structured approach using frameworks or benchmarks.
• Strong communication with technical and non-technical stakeholders.
• Adaptability to move across projects and customers.

Responsibilities

• Red team conversational AI models and agents focusing on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data; annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly; produce reports, datasets, and attack cases for customer action.

Skills

English fluency

Norwegian fluency

Red teaming experience

Structured testing

Strong communication

Adaptability

Job description

Mercor is seeking AI Safety Experts — English & Norwegian for a remote contract role. You will test AI models to uncover jailbreaks, prompt injections, misuse cases, and biases across multilingual contexts.

Ideal candidates have prior red-teaming experience in AI adversarial work or cybersecurity, and can apply structured testing using benchmarks. Excellent communication with diverse stakeholders and adaptability to work across multiple projects are essential.