AI Safety Red Teamer

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

📋 Description

• Create adversarial prompts to rigorously evaluate cutting-edge AI models.

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

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

• Record vulnerabilities and assist in compiling safety benchmarking and red-teaming documentation.

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

• Engage in projects aimed at training and improving AI systems.

⛳️ Requirements

• A 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 similar area.

• Exceptional analytical reasoning abilities.

• Experience in prompt design.

• Strong written communication skills.

• Background in designing adversarial prompts or assessing cutting-edge AI systems.

• Knowledge of jailbreak testing, prompt engineering, or adversarial evaluation techniques.

• Proficiency in one or more grey-area domains, including cybersecurity, biosecurity, political content, misinformation, or scientific safety.

• Must not be an H1-B or STEM OPT candidate, as Mercor cannot accommodate those applicants.

🏝️ Benefits

• Fully remote position.

• Flexible work schedule that allows completion at your convenience.

• Weekly payments through Stripe or Wise based on services rendered.

• Project timelines may be extended, shortened, or concluded early based on needs and performance.

• Competitive compensation.

• Opportunity to work alongside leading AI researchers and safety teams.

• Chance to influence the development of the next generation of AI systems.

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

• Reasonable accommodations available upon request.