Bilingual AI Safety Red Teamer (Remote)

Mercor; Lisboa; Sur place; EUR 45 000 - 65 000; Plein temps

Résumé du poste

Mercor is seeking a remote Red Team data expert to test and strengthen AI systems by identifying vulnerabilities, generating attack datasets, and documenting reproducible results. You will apply structured methodologies and communicate risks clearly to diverse stakeholders across global projects.

The role emphasizes adaptive work across multiple clients, with a focus on safe, high-quality data for adversarial AI testing.

Qualifications

• Red team experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to apply frameworks, taxonomies, benchmarks and playbooks.
• Clear communication of risks to technical and non-technical audiences.

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.
• Document reproducibly: produce reports, datasets, and attack cases customers can act on.
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent.

Connaissances

Red team experience

Adversarial thinking

Structured approach

Communication skills

Adaptability

Description du poste

Mercor is seeking a remote Red Team data expert to test and strengthen AI systems by identifying vulnerabilities, generating attack datasets, and documenting reproducible results. You will apply structured methodologies and communicate risks clearly to diverse stakeholders across global projects.

The role emphasizes adaptive work across multiple clients, with a focus on safe, high-quality data for adversarial AI testing.