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

📋 Description

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

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

• Assess model resilience in areas such as misinformation, cyber threats, biosecurity, fraud, political content, and other sensitive sectors.

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

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

• Engage in projects that focus on the training and improvement of AI systems.

• Manage project tasks according to an independent timeline; project durations may vary based on requirements 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 relevant professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or related areas.

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

• 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 methodologies for adversarial evaluation.

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

• Must be capable of functioning as an independent contractor.

• H1-B and STEM OPT candidates cannot be supported.