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

📋 Description

• Develop adversarial prompts to evaluate and challenge cutting-edge AI models

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

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

• Record vulnerabilities and aid in the creation of safety benchmarking and red-teaming reports

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

• Engage in project-based tasks for Mercor's partner AI labs and enterprises dedicated to training and improving frontier 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

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

• Experience in crafting adversarial prompts or assessing frontier AI systems

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

• Preferred: knowledge of jailbreak testing, prompt engineering, or adversarial evaluation methods

• Preferred: expertise in one or more grey-area sectors, such as cybersecurity, biosecurity, political content, misinformation, or scientific safety

• Must be capable of functioning as an independent contractor

• H1-B and STEM OPT candidates are not eligible