Remote AI Safety Red Team Engineer

Mercor; Amsterdam; Remote; EUR 70,000 - 110,000; Full time

Job summary

Mercor is assembling a remote AI red team focused on adversarial testing to surface vulnerabilities in conversational models. You will probe models with jailbreaks, injections, and misuse cases, generating high-quality human data and reproducible reports for customers.

The role emphasizes structured testing using frameworks and clear communication of risks to technical and non-technical stakeholders, with flexibility to move across projects and clients.

Qualifications

• Prior red‑team experience with AI adversarial work, cybersecurity, or socio‑technical probing.
• Ability to follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Strong written and verbal communication to explain risks to technical and non‑technical stakeholders.

Responsibilities

• 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.

Skills

Red team

Adversarial AI

Cybersecurity

Socio-technical risk

Frameworks/benchmarks

Clear communication

Adaptable across projects

Adversarial mindset

Job description

Mercor is assembling a remote AI red team focused on adversarial testing to surface vulnerabilities in conversational models. You will probe models with jailbreaks, injections, and misuse cases, generating high-quality human data and reproducible reports for customers.

The role emphasizes structured testing using frameworks and clear communication of risks to technical and non-technical stakeholders, with flexibility to move across projects and clients.