AI Red Team Specialist — Adversarial Testing (Remote)

Mercor; Quezon City; Remote; PHP 3,652,000 - 7,304,000; Full time

Job summary

Mercor seeks a remote Red Team Data Specialist to probe AI outputs, surface vulnerabilities, and generate adversarial data for safer models. The role is text-based and focuses on bias, misinformation, and harmful content areas with clear guidelines and wellness resources.

You’ll annotate failures, classify risks, follow benchmarks, and document reproducible reports and datasets for customers to act on. English and Vietnamese fluency is required.

Qualifications

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Ability to follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Clear communication of 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 teaming

Adversarial ML

Cybersecurity

Structured testing

Technical communication

Job description

Mercor seeks a remote Red Team Data Specialist to probe AI outputs, surface vulnerabilities, and generate adversarial data for safer models. The role is text-based and focuses on bias, misinformation, and harmful content areas with clear guidelines and wellness resources.

You’ll annotate failures, classify risks, follow benchmarks, and document reproducible reports and datasets for customers to act on. English and Vietnamese fluency is required.