AI Safety Red Teamer

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

📋 Description

• Develop adversarial prompts aimed at evaluating the resilience of cutting-edge AI models.

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

• Assess model robustness in relation to misinformation, cyber threats, biosecurity, fraud, political content, and other delicate areas.

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

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

• Engage in project initiatives for Mercor's partner AI labs and organizations dedicated to training and refining AI systems.

⛳️ Requirements

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

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

• Exceptional analytical reasoning, prompt design, and written communication abilities.

• Proven experience in designing adversarial prompts or evaluating advanced AI systems.

• Preferred experience in AI Red Teaming, Reinforcement Learning from Human Feedback (RLHF), Supervised Fine-Tuning (SFT), AI Alignment, or Trust & Safety.

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

• Expertise in nuanced domains such as cyber threats, biosecurity, political content, misinformation, or scientific safety is preferred.

• Must be authorized to work in one of the specified locations.

• Mercor is unable to sponsor H1-B or STEM OPT candidates at this time.

🏝️ Benefits

• Fully remote working environment.

• Flexible schedule; complete work on your own terms.

• Weekly payments processed through Stripe or Wise.

• Project durations may be extended, shortened, or concluded early based on requirements and performance.

• Competitive compensation.

• Opportunity to collaborate with top AI researchers and safety teams.

• Chance to impact frontier AI safety and model advancement.

• Up to $340 for each successful referral, subject to referral constraints.

• Reasonable accommodations available upon request.