Remote AI Adversarial Safety Specialist (English & Vietnamese)

Mercor; Philippines; On-site; PHP 1,439,000 - 2,117,000; Part time

Job summary

Mercor is seeking AI Safety Experts—English & Vietnamese—to safely test and probe AI systems. This remote contract role involves rigorous red teaming of conversational models and documenting findings for customers.

You’ll annotate failures, assess vulnerabilities, and communicate risks clearly to both technical and non-technical stakeholders. Prior adversarial ML or cybersecurity experience is preferred, with contributions to ethics and risk minimization.

Qualifications

• Fluent in English and Vietnamese.
• Prior experience in red teaming, AI adversarial work, or cybersecurity.
• Ability to explain risks clearly to both technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents by conducting jailbreaks, prompt injections, and bias exploitation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases for customer action.
• Review AI outputs on sensitive topics like bias and misinformation, with optional participation in higher-sensitivity projects.

Skills

English fluency

Vietnamese fluency

Red teaming

Risk communication

Adversarial ML

Cybersecurity

Creative probing

Stakeholder communication

Job description

Mercor is seeking AI Safety Experts—English & Vietnamese—to safely test and probe AI systems. This remote contract role involves rigorous red teaming of conversational models and documenting findings for customers.

You’ll annotate failures, assess vulnerabilities, and communicate risks clearly to both technical and non-technical stakeholders. Prior adversarial ML or cybersecurity experience is preferred, with contributions to ethics and risk minimization.