Remote AI Safety Red Team Engineer

Obsidian; Kuala Lumpur; On-site; MYR 368,000 - 613,000; Full time

Job summary

Mercor is building a red team for AI safety testing. This remote role involves probing conversational AI models with adversarial inputs, surface vulnerabilities, and producing actionable data for customers.

Ideal candidates bring experience in AI adversarial work, cybersecurity, and a structured approach using benchmarks and playbooks, with strong communication to both technical and non-technical stakeholders.

Qualifications

• Red team AI adversarial work or cybersecurity experience.
• Curious and adversarial mindset focused on breaking systems.
• Structured thinker using benchmarks or playbooks.
• Ability to explain risks clearly to technical and non-technical audiences.

Responsibilities

• Red team conversational AI models: jailbreaks, prompt injections, misuse cases.
• Generate high-quality human data: annotate failures, classify vulnerabilities.
• 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 teaming

AI adversarial work

Cybersecurity

Structured frameworks

Communication

Adaptability

Job description

Mercor is building a red team for AI safety testing. This remote role involves probing conversational AI models with adversarial inputs, surface vulnerabilities, and producing actionable data for customers.

Ideal candidates bring experience in AI adversarial work, cybersecurity, and a structured approach using benchmarks and playbooks, with strong communication to both technical and non-technical stakeholders.