Remote AI Safety Red Team Specialist

Mercor; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

Mercor is seeking a remote red team specialist to probe AI models for vulnerabilities through adversarial testing. The role focuses on text-based evaluation of safety boundaries, bias, and potential misuses, with participation in sensitive projects supported by guidelines.

The work is distributed across projects and customers, with clear communication of risks. The ideal candidate has red teaming experience in AI adversarial work, cybersecurity or socio-technical probing, and thrives on

Qualifications

• Prior red teaming experience in AI adversarial work, cybersecurity or socio-technical probing.
• Curious and adversarial mindset, able to push systems to breaking points.
• Structured thinker using frameworks or benchmarks, not random hacks.
• Strong written and verbal communication to explain risks to tech and non-tech stakeholders.
• Adaptable to 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

English

Malay

Job description

Mercor is seeking a remote red team specialist to probe AI models for vulnerabilities through adversarial testing. The role focuses on text-based evaluation of safety boundaries, bias, and potential misuses, with participation in sensitive projects supported by guidelines.

The work is distributed across projects and customers, with clear communication of risks. The ideal candidate has red teaming experience in AI adversarial work, cybersecurity or socio-technical probing, and thrives on