Remote AI Adversarial Tester (English/Vietnamese)

Mercor; Philippines; Remote; USD 90,000 - 150,000; Full time

Job summary

Mercor is seeking a seasoned AI red team specialist to join our remote team. You will test conversational AI models via jailbreaks, prompt injections, and bias exploration, generating actionable adversarial data for safer systems.

We value curiosity, a structured testing approach, and the ability to communicate risk clearly to technical and non-technical stakeholders across multiple projects and customers. You'll document reproducible results and follow established taxonomies to strengthen

Qualifications

• Red team experience in AI adversarial work or cybersecurity.
• Curious and adversarial mindset that pushes systems to limits.
• Structured approach using benchmarks or playbooks.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation.
• Generate high-quality human data: annotate failures and flag 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

Cybersecurity

Adversarial ML

Structured frameworks

Communication

Adaptable

Tools

Penetration testing

Reverse engineering

Job description

Mercor is seeking a seasoned AI red team specialist to join our remote team. You will test conversational AI models via jailbreaks, prompt injections, and bias exploration, generating actionable adversarial data for safer systems.

We value curiosity, a structured testing approach, and the ability to communicate risk clearly to technical and non-technical stakeholders across multiple projects and customers. You'll document reproducible results and follow established taxonomies to strengthen