AI Safety Red Teamer — Remote

Mercor; Lisboa; Presencial; EUR 69 000 - 104 000; Tempo integral

Resumo da oferta

Mercor is seeking a remote AI red team professional to probe conversational AI models through jailbreaks, prompt injections, and misuse cases. You will generate high-quality human data, annotate vulnerabilities, and flag systemic risks using structured frameworks to keep testing consistent.

The role emphasizes documenting reproducible attack cases and reports that help customers strengthen their AI systems.

Qualificações

• Red team experience in AI adversarial work or cybersecurity.
• Ability to follow taxonomies, benchmarks, and playbooks.
• Strong communication to technical and non-technical stakeholders.
• Adaptability across projects and customers.
• Curiosity and adversarial mindset.

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

AI adversarial testing

Cybersecurity

Socio-technical probing

Structured framework usage

Clear communication

Adaptability across projects

Creative thinking

Descrição da oferta de emprego

Mercor is seeking a remote AI red team professional to probe conversational AI models through jailbreaks, prompt injections, and misuse cases. You will generate high-quality human data, annotate vulnerabilities, and flag systemic risks using structured frameworks to keep testing consistent.

The role emphasizes documenting reproducible attack cases and reports that help customers strengthen their AI systems.