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

📋 Description

• Create adversarial prompts to rigorously test frontier AI models

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

• Assess model resilience in areas such as misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive fields

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

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

• Engage in projects aimed at training and refining AI systems

• Project timelines may be adjusted, extended, or concluded early based on needs 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 similar area

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

• Experience in creating adversarial prompts or assessing frontier AI systems

• Preferred: Background 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: Proficiency in one or more ambiguous domains such as cybersecurity, biosecurity, political content, misinformation, or scientific safety

• Must not be an H1-B or STEM OPT candidate