Remote AI Red Teamer — Advanced Adversarial Testing

Mercor; Remote; USD 10,000 - 60,000; Full time

Job summary

A technology firm specializing in AI safety is seeking a Remote AI RedTeamer to conduct adversarial testing on AI systems. You will red team conversational AI models, generate high-quality human data, and document testing processes. Ideal candidates are fluent in English and German, have prior red teaming or cybersecurity experience, and excel at communicating technical risks. This is a full-time or part-time remote contract role, offering competitive rates aligned with expertise and workload.

Benefits

Competitive rates based on experience

Opportunity to enhance AI robustness

Work in a high-impact area of AI safety

Qualifications

• Prior experience in red teaming AI systems or cybersecurity.
• Fluent in English and German at a native level.
• Ability to communicate risks clearly to various stakeholders.

Responsibilities

• Red team AI models by performing jailbreaks and bias exploitation.
• Generate high-quality human data by annotating failures and classifying vulnerabilities.
• Document testing processes to produce actionable reports for clients.

Skills

Adversarial AI Testing

Cybersecurity

Fluent in English

Fluent in German

Job description

A technology firm specializing in AI safety is seeking a Remote AI RedTeamer to conduct adversarial testing on AI systems. You will red team conversational AI models, generate high-quality human data, and document testing processes. Ideal candidates are fluent in English and German, have prior red teaming or cybersecurity experience, and excel at communicating technical risks. This is a full-time or part-time remote contract role, offering competitive rates aligned with expertise and workload.