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 policy breaches.

• Assess model resilience in the face of misinformation, cyber threats, biosecurity issues, fraud, political content, and various sensitive areas.

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

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

• Contribute to the security and fortification of the upcoming generation of frontier AI models.

• 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 similar domain.

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

• Experience in crafting adversarial prompts or evaluating cutting-edge AI systems.

• Preferred experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety.

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

• Expertise in one or more grey-area domains, such as cyber, biosecurity, political content, misinformation, or scientific safety is preferred.

• Candidates must not require H1-B or STEM OPT sponsorship; Mercor is unable to support H1-B or STEM OPT applicants.