AI Safety Red Teamer

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

📋 Description

• Create adversarial prompts to rigorously evaluate frontier AI models

• Detect jailbreaks, unsafe behaviors, hallucinations, and policy shortcomings

• Assess model resilience across misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas

• Record vulnerabilities and aid in safety benchmarking and red-teaming documentation

• Partner with AI researchers to enhance model alignment, robustness, and safety

• Engage in projects aimed at training and improving AI systems

⛳️ Requirements

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related field

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

• Excellent analytical reasoning, prompt design, and written communication abilities

• Experience in crafting adversarial prompts or assessing frontier AI systems

• Preferred experience in AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety

• Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation techniques preferred

• Preferred expertise in cybersecurity, biosecurity, political content, misinformation, or scientific safety

• Currently unable to support H1-B or STEM OPT candidates

🏝️ Benefits

• Fully remote position

• Flexible work hours / autonomy to set your own schedule

• Weekly payments via Stripe or Wise

• Project timelines may be adjusted, shortened, or concluded early based on requirements and performance

• Competitive compensation

• Opportunity to work alongside top AI researchers and safety teams

• Referral bonuses of up to $340 for successful referrals, subject to conditions

• Reasonable accommodations available upon request