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

📋 Description

• Develop adversarial prompts aimed at stress-testing advanced AI models.

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

• Assess model resilience in the context of misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas.

• Record vulnerabilities and contribute to safety benchmarking and red-teaming documentation.

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

• Engage in projects dedicated to the training and improvement of AI systems.

• Manage your workload on your own timetable, with project durations potentially adjusted based on needs and performance.

⛳️ 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 comparable area.

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

• Proven experience in designing adversarial prompts or assessing advanced AI systems.

• Preferred: experience 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: specialization in one or more grey-area sectors, including cybersecurity, biosecurity, political content, misinformation, or scientific safety.

• Engagement as an independent contractor.

• Must be able to work independently without H1-B or STEM OPT support.