Remote AI Safety Red Team Specialist

Obsidian; Kuala Lumpur; Remote; MYR 368,000 - 531,000; Full time

Job summary

Mercor is building a remote red team to probe AI models with adversarial inputs and evaluate outputs touching sensitive topics. You will generate high-quality human data, annotate vulnerabilities, and flag systemic risks while following established benchmarks and playbooks. All work is text-based and supported by wellness resources.

The role requires clear communication to both technical and non-technical stakeholders and offers the flexibility to move across projects and customers.

Qualifications

• Have red teaming or adversarial AI testing experience.
• Ability to push systems to breaking points with structured methods.
• Strong communication to explain risks to technical and non-technical stakeholders.

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

Adversarial ML

Cybersecurity

Structured testing

Technical writing

Job description

Mercor is building a remote red team to probe AI models with adversarial inputs and evaluate outputs touching sensitive topics. You will generate high-quality human data, annotate vulnerabilities, and flag systemic risks while following established benchmarks and playbooks. All work is text-based and supported by wellness resources.

The role requires clear communication to both technical and non-technical stakeholders and offers the flexibility to move across projects and customers.