Remote AI Safety Red Team Specialist

Mercor; Kuala Lumpur; On-site; MYR 90,000 - 150,000; Full time

Job summary

Mercor is assembling a remote red team to probe AI models for safety. Join a team focusing on adversarial inputs, bias surfaces, and high-sensitivity content handling with clear guidelines. Collaboration across stakeholders is emphasized as you help strengthen AI systems.

You will generate reproducible artifacts, evaluate multiple scenarios, and help Mercor deliver safer AI to customers while maintaining strict wellness guidelines and optional participation in sensitive tasks.

Qualifications

• Red team AI models and agents testing including jailbreaks and prompt injections.
• Annotate failures, classify vulnerabilities, and flag systemic risks.
• Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly: produce reports and datasets for customers.

Responsibilities

• Red team conversational AI models and agents, including jailbreaks and prompt injections.
• Generate high-quality human data by annotating failures and vulnerabilities.
• Apply structure using taxonomies, benchmarks and playbooks.
• Document reproducibly with reports and attack case datasets.

Skills

Red teaming

Adversarial AI

Cybersecurity

Structured frameworks

Communication

Tools

Job description

Mercor is assembling a remote red team to probe AI models for safety. Join a team focusing on adversarial inputs, bias surfaces, and high-sensitivity content handling with clear guidelines. Collaboration across stakeholders is emphasized as you help strengthen AI systems.

You will generate reproducible artifacts, evaluate multiple scenarios, and help Mercor deliver safer AI to customers while maintaining strict wellness guidelines and optional participation in sensitive tasks.