AI Safety Red Teamer

This is a fully remote position, open to applicants in United States.

📋 Description

• Create adversarial prompts to challenge and evaluate frontier AI models.

• Detect jailbreaks, unsafe behaviors, hallucinations, and failures in policy compliance.

• Assess model resilience in the contexts of misinformation, cybersecurity, biosecurity, fraud, political content, and other critical areas.

• Record vulnerabilities and assist in the development of safety benchmarking and red-teaming reports.

• Collaborate with AI researchers to enhance model alignment, robustness, and safety measures.

• Engage in projects focused on training and improving frontier AI systems.

⛳️ Requirements

• A Bachelor's degree or higher in fields such as Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a similar area.

• Over 5 years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related domain.

• Exceptional skills in analytical reasoning, prompt design, and written communication.

• Proven experience in designing adversarial prompts or assessing frontier AI systems.

• Required to be based in one of the specified eligible countries or territories.

• H1-B and STEM OPT candidates are not eligible.

🏝️ Benefits

• Completely remote work environment.

• Flexible working hours, allowing you to set your own schedule.

• Weekly payments through Stripe or Wise.

• Opportunities for project extensions.

• Competitive compensation.

• Collaboration with top AI researchers and safety teams.

• Reasonable accommodations available upon request.

• Referral bonuses of up to $340 for each successful referral.