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 shortcomings.

• Assess model resilience concerning misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas.

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

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

• Engage in projects aimed at training and improving AI systems.

• Complete tasks according to an independent schedule.

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

⛳️ Requirements

• 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 related discipline.

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

• Proven experience in designing adversarial prompts or evaluating 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 methods.

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

• Must be capable of functioning as an independent contractor.

• H1-B and STEM OPT applicants are not eligible.