Ai Safety Specialist - Fully Remote | Up To $25/Hr

Mercor; Sydney; Remote; AUD 33,000 - 49,000; Full time

Job summary

Mercor is seeking AI Safety Experts to test and stress AI models in a remote contract role. You will perform red team testing, document findings, and develop datasets and attack cases for clients.

The role requires native English and Vietnamese, strong adversarial AI experience, and the ability to clearly explain risks to diverse stakeholders. Independent work style and adaptability are essential for success in this position.

Qualifications

• Native fluency in English and Vietnamese.
• Proven red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to explain risks clearly to both technical and non-technical stakeholders.
• Able to adapt across projects and customers.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks and misuse cases.
• Annotate failures, classify vulnerabilities, and flag systemic risks to generate high-quality data.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly to produce reports, datasets, and attack cases for customers.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English proficiency

Vietnamese proficiency

Red teaming

Risk communication

Adaptability

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 maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

• Native fluency in English and 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.
• Adaptability to thrive across projects and customers.

Preferred

• Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Cybersecurity skills: penetration testing, exploit development, reverse engineering.
• Socio-technical risk expertise: harassment/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
• For any help or support, reach out to: [e-mail]