Remote AI Safety Red Team Specialist

Mercor; Lisboa; Teletrabalho; EUR 78 000 - 130 000; Tempo integral

Resumo da oferta

Mercor is building a dedicated red team to test AI safety by probing conversational models through jailbreaks, prompt injections, and bias scenarios. This role centers on generating high-quality human data, classifying vulnerabilities, and documenting findings with structured reports that help customers strengthen AI systems.

The work spans multiple projects and clients, with a strong emphasis on clear communication and reproducibility.

Qualificações

• Red team experience with AI adversarial work or cybersecurity.
• Clear, structured thinking and the ability to follow frameworks or playbooks.

Responsabilidades

• 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

Conhecimentos

Red team experience

Adversarial mindset

Structured approach

Communication

Adaptability

Descrição da oferta de emprego

Mercor is building a dedicated red team to test AI safety by probing conversational models through jailbreaks, prompt injections, and bias scenarios. This role centers on generating high-quality human data, classifying vulnerabilities, and documenting findings with structured reports that help customers strengthen AI systems.

The work spans multiple projects and clients, with a strong emphasis on clear communication and reproducibility.