Remote AI Safety Red Team Specialist

Mercor; Brussel Hoofdstad; Sur place; EUR 77 000 - 112 000; Plein temps

Résumé du poste

Mercor is assembling a remote red team focused on testing AI systems for vulnerabilities, bias, and misuses. You will simulate adversarial scenarios, annotate failures, and document actionable attack cases for customers, applying structured playbooks and taxonomies to ensure repeatable results.

The role emphasizes rigorous testing, clear risk communication, and adaptability across projects and clients, with emphasis on safety, robustness, and trustworthy AI outcomes.

Qualifications

• Prior red teaming experience with AI adversarial work or cybersecurity is required.
• Ability to follow frameworks, benchmarks, and playbooks.
• Strong communication skills to explain risks to technical and non-technical stakeholders.

Responsabilités

• 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.

Connaissances

Red teaming

AI adversarial testing

Cybersecurity

Structured thinking

Stakeholder communication

Adaptability

Description du poste

Mercor is assembling a remote red team focused on testing AI systems for vulnerabilities, bias, and misuses. You will simulate adversarial scenarios, annotate failures, and document actionable attack cases for customers, applying structured playbooks and taxonomies to ensure repeatable results.

The role emphasizes rigorous testing, clear risk communication, and adaptability across projects and clients, with emphasis on safety, robustness, and trustworthy AI outcomes.