AI Adversarial Specialist - Fully Remote | Upto $25/hr

mercor; United States; Remote; USD 23,000 - 34,000; Part time

Job summary

Mercor, a San Francisco-based AI safety firm, is seeking AI Safety Experts — English & Vietnamese for remote contract work. You will red team conversational AI models, generate high-quality data, document findings, and report vulnerabilities to help customers harden systems.

The role requires independent work, strong communication with technical and non-technical stakeholders, and experience in adversarial ML or cybersecurity.

Qualifications

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

Responsibilities

• Red team conversational AI models 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 ensure consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to uncover vulnerabilities and improve AI model performance.

Skills

English fluency

Vietnamese fluency

Red team experience

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 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 ensure consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to uncover vulnerabilities and improve AI model performance.

Qualifications Must-Have

• Fluent Language Skills Required: English & Vietnamese.
• Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Preferred

• Experience with Adversarial ML , Cybersecurity , or socio-technical risk analysis.
• Skills in creative probing such as psychology, acting, or writing.

Originally posted on Himalayas