Remote AI Safety & Adversarial Testing Specialist

Mercor; Stockholms kommun; On-site; SEK 1,136,000 - 1,705,000; Full time

Job summary

Mercor is assembling a remote AI safety red team to probe conversational models with adversarial inputs, surface vulnerabilities, and generate actionable data for customers. You will annotate failures, follow structured taxonomies and playbooks, document reproducible attack cases, and collaborate across projects to strengthen system robustness and safety.

Ideal candidates bring prior red-teaming or cybersecurity experience and can explain risks clearly to both technical and non-technical

Qualifications

• You have prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• You are curious and adversarial, pushing systems to breaking points.
• You are structured and use frameworks or benchmarks, not random hacks.
• You are communicative and can explain risks to technical and non-technical stakeholders.
• You are adaptable and able to move 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 teaming

Adversarial ML

Cybersecurity

Structured testing

Communication

Job description

Mercor is assembling a remote AI safety red team to probe conversational models with adversarial inputs, surface vulnerabilities, and generate actionable data for customers. You will annotate failures, follow structured taxonomies and playbooks, document reproducible attack cases, and collaborate across projects to strengthen system robustness and safety.

Ideal candidates bring prior red-teaming or cybersecurity experience and can explain risks clearly to both technical and non-technical