Remote AI Safety Red Team Expert

Mercor; Brussel Hoofdstad; À distance; EUR 70 000 - 110 000; Plein temps

Résumé du poste

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that makes AI safer for customers.

You will annotate failures, classify vulnerabilities, and document reproducible reports and attack cases. Fluent English and Dutch are required; prior red‑team or cybersecurity experience is preferred. You’ll work across projects and customers, adapting to new themes while following clear guidelines.

Qualifications

• Experience in AI red teaming or cybersecurity testing.
• Ability to surface vulnerabilities and surface actionable insights.
• Ability to document findings clearly for technical and non-technical stakeholders.

Responsabilités

• Red team conversational AI models and event-driven tests for safety vulnerabilities.
• Annotate failures, classify vulnerabilities, and flag systemic risks.
• Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly: produce reports, datasets, and attack cases.

Connaissances

Red team experience

AI adversarial work

Cybersecurity

Socio-technical probing

Structured thinking

Clear communication

Adaptive

Description du poste

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that makes AI safer for customers.

You will annotate failures, classify vulnerabilities, and document reproducible reports and attack cases. Fluent English and Dutch are required; prior red‑team or cybersecurity experience is preferred. You’ll work across projects and customers, adapting to new themes while following clear guidelines.