AI Safety Red Teamer

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

📋 Description

• Create adversarial prompts to rigorously test advanced AI models

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

• Assess model resilience in areas such as misinformation, cyber threats, biosecurity, fraud, political content, and other sensitive topics

• Record vulnerabilities and assist in creating safety benchmarks and red-teaming documentation

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

• Engage in projects aimed at training and improving 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 related area

• A minimum of 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 advanced AI systems

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

• Familiarity with methodologies for jailbreak testing, prompt engineering, or adversarial evaluation is preferred

• Knowledge in one or more grey-area domains, including cyber security, biosecurity, political content, misinformation, or scientific safety is preferred

• Must not require H1-B or STEM OPT support at this time

🏝️ Benefits

• Fully remote work

• Flexible scheduling

• Weekly payments through Stripe or Wise based on services provided

• Opportunity to collaborate with leading AI researchers and safety teams

• Involvement in cutting-edge adversarial testing initiatives

• Opportunity to influence the responses of AI systems to real-world safety challenges

• Competitive compensation

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

• Reasonable accommodations available upon request