Remote AI Adversarial Red Teamer – Bilingual

Mercor; Kuala Lumpur; Remote; MYR 286,000 - 490,000; Full time

Job summary

Mercor is assembling a remote red team member to challenge AI systems with adversarial inputs, focusing on safety, bias, and risk assessment across client projects. This role involves analyzing outputs, annotating vulnerabilities, and producing reproducible attack cases and reports to help customers strengthen their AI systems.

You bring prior red teaming experience (AI adversarial work, cybersecurity), a curious adversarial mindset, structured thinking, and excellent communication to explain

Qualifications

• Prior red teaming experience in AI adversarial work or cybersecurity
• Curious and adversarial mindset, push systems to limits
• Structured approach using frameworks, benchmarks, and playbooks
• Ability to clearly explain risks to technical and non-technical stakeholders
• Adaptable across projects and customers

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 mindset

Adversarial thinking

Structured problem solving

Clear communication

Adaptability

Job description

Mercor is assembling a remote red team member to challenge AI systems with adversarial inputs, focusing on safety, bias, and risk assessment across client projects. This role involves analyzing outputs, annotating vulnerabilities, and producing reproducible attack cases and reports to help customers strengthen their AI systems.

You bring prior red teaming experience (AI adversarial work, cybersecurity), a curious adversarial mindset, structured thinking, and excellent communication to explain