Ai Safety Expert - Red Teamer

Mercor; San Francisco (CA); Hybrid; GBP 21,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts to remotely test and critique conversational AI systems, focusing on jailbreaks, bias, and risk exposure. You will generate high-quality human data, annotate issues, and draft reproducible reports for customers.

Ideal candidates have experience in AI adversarial work or cybersecurity and can clearly communicate risk to diverse stakeholders. This is a remote, contract role with competitive hourly compensation.

Qualifications

• Fluent in English and Bengali.
• Prior red teaming in AI adversarial work or cybersecurity.
• Ability to communicate risks clearly to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents, focusing on jailbreaks and prompt injections.
• Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks for testing.
• Document reproducibly with reports, datasets, and attack cases.
• Review AI outputs on sensitive topics; participate in higher-sensitivity projects as guided.

Skills

English

Bengali

Red team experience

AI adversarial work

Cybersecurity

Stakeholder communication

Tools

Adversarial ML

Cybersecurity

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 & Bengali
Type: Contract
Compensation: $20–$22/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 using taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases for customer action.
• Review AI outputs on sensitive topics like bias and misinformation. Participation in higher-sensitivity projects is optional and supported by guidelines.

Qualifications

Must-Have

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

Preferred

• Experience with Adversarial ML, Cybersecurity, and socio-technical risk analysis.
• Creative probing skills in psychology, acting, or 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]