AI Safety Expert - Red Team

Mercor; San Francisco (CA); Remote; USD 23,000 - 34,000; Full time

Job summary

Mercor, headquartered in San Francisco, is seeking AI Safety Experts to work remotely on English and Malay language safety testing for AI models. This contract role focuses on red-teaming models, data generation, and reproducible reporting to help clients understand and mitigate risks.

Applicants should have strong English and Malay proficiency, prior AI adversarial testing experience, and excellent communication skills for explaining risks to diverse stakeholders.

Qualifications

• Fluent in English and Malay.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English

Malay

Red teaming

Cybersecurity

Communication

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 & Malay
Type: Contract
Compensation: $17–$25/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly. 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

• Fluent in English and Malay.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.

Preferred

• Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
• Knowledge in socio-technical risk: 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]