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

📋 Description

• Create adversarial prompts to rigorously test cutting-edge AI models

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

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

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

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

• 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

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

• Experience in designing adversarial prompts or assessing advanced AI systems

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

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

• Preferred: Expertise in one or more grey-area fields, including cybersecurity, biosecurity, political content, misinformation, or scientific safety

• Must not require H1-B or STEM OPT support; Mercor is currently unable to sponsor H1-B or STEM OPT candidates

• Engagement as an independent contractor