Ai Safety Expert - Red Teamer

Mercor; Sydney; Remote; AUD 34,000 - 50,000; Full time

Job summary

Mercor connects elite creative and technical talent with AI labs. We are seeking AI Safety Experts (English & Vietnamese) on a remote contract to help stress test and improve safety in AI systems.

You will red team models, generate data, and document findings for clients, explaining risks to technical and non-technical stakeholders. Prior AI adversarial or cybersecurity experience is required or preferred, with strong communication skills.

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 AI models and agents via jailbreaks, prompt injections, and bias exploitation.
• Generate high-quality data by annotating failures, classifying vulnerabilities, and flagging risks.
• Apply taxonomies and playbooks to ensure consistent testing.
• Document reproducibly with reports, datasets, and attack cases for customers.
• Review AI outputs on sensitive topics, with optional higher-sensitivity work.

Skills

English fluency

Vietnamese

Red teaming

AI adversarial work

Cybersecurity

Explain risks

Creative probing

Psychology

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position: AI Safety Experts - English & Vietnamese
Type: Contract
Compensation: $17-$25/hour
Location: Remote

Role 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.

Qualifications

Must-Have

• 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.

Preferred

• Experience with adversarial ML, cybersecurity, and socio-technical risk.
• Skills in creative probing, psychology, acting, or writing for unconventional adversarial thinking.