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

📋 Description

• Create adversarial prompts to rigorously evaluate advanced AI models.

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

• Assess the robustness of models in various sensitive areas, including misinformation, cybersecurity, biosecurity, fraud, and political content.

• Record vulnerabilities and assist in the development of 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 refining 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 closely related area.

• Excellent analytical reasoning, prompt design capabilities, and written communication skills.

• Proven experience in crafting adversarial prompts or assessing advanced 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 techniques.

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

• Must not require H-1B or STEM OPT support; Mercor is unable to accommodate H-1B or STEM OPT candidates.