About the job
Mercorconnects elite creative and technical talent with leading AI research labs.
Headquartered in San Francisco, our investors includeBenchmark,General Catalyst,Peter Thiel,Adam D'Angelo,Larry Summers, andJack Dorsey.
Position:AI Safety Experts – English & Vietnamese
Type:Contract
Compensation:$17–$25/hour
Location:Remote
Role Responsibilities
Red team conversationalAI modelsand agents to identify jailbreaks, prompt injections, and misuse cases.
Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
Workindependently and asynchronouslyto meet deadlines while improvingAI model performance.
Qualifications
Must-Have




Native fluency inEnglishandVietnamese.
Prior red teaming experience inAI adversarial work,cybersecurity, or socio-technical probing.
Ability to explain risks clearly to technical and non-technical stakeholders.
Adaptability to thrive across projects and customers.
Preferred
Experience inAdversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
Cybersecurityskills: penetration testing, exploit development, reverse engineering.
Socio-technical risk expertise: harassment/disinfo probing, abuse analysis, conversationalAI testing.
Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.
#J-*****-Ljbffr

📌 Ai Safety Specialist - Fully Remote (Perth)
🏢 Mercor
📍 Perth