Remote AI Safety Red Team Specialist

Mercor; Kuala Lumpur; On-site; MYR 120,000 - 200,000; Full time

Job summary

Mercor is assembling a remote red team to probe AI models for safety, focusing on bias, misinformation, and harmful outputs with clear guidelines and wellness support. You will work on high-quality data generation, annotating failures, and producing reproducible reports and attack cases to help customers strengthen their AI systems.

Ideal candidates bring adversarial mindset, structured testing, and strong communication to explain risks to technical and non-technical stakeholders while adapting

Qualifications

• You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing)
• You’re curious and adversarial: you instinctively push systems to breaking points
• You’re structured: you use frameworks or benchmarks, not just random hacks
• You’re communicative: you explain risks clearly to technical and non-technical stakeholders
• You’re adaptable: thrive on moving 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 teaming experience

Adversarial AI

Cybersecurity

Structured thinking

Communication

Tools

Penetration testing

Reverse engineering

RLHF/DPO attacks

Model extraction

Job description

Mercor is assembling a remote red team to probe AI models for safety, focusing on bias, misinformation, and harmful outputs with clear guidelines and wellness support. You will work on high-quality data generation, annotating failures, and producing reproducible reports and attack cases to help customers strengthen their AI systems.

Ideal candidates bring adversarial mindset, structured testing, and strong communication to explain risks to technical and non-technical stakeholders while adapting