AI Red Teamer, CBRNE (Remote)

📋 Description

• Design technically grounded adversarial prompts that test whether models provide meaningful uplift
• Evaluate model outputs for technical accuracy, assessing whether responses contain genuinely
• Probe dual-use knowledge boundaries, testing how models handle queries that blend legitimate
• Test multi-step and multi-turn attack chains that simulate how a motivated actor might extract
• Score model responses against structured harm taxonomies and severity rubrics calibrated to
• Document findings with clear technical reasoning, including what a response gets right, what it

🎯 Requirements

• Graduate-level education or equivalent professional experience in a relevant CBRNE field
• Ability to evaluate the technical accuracy and real-world consequence of model outputs in your
• Understanding of dual-use research concerns and the distinction between open-source knowledge and
• Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.)
• Creative, adversarial problem-solving skills
• Clear and precise written communication, including the ability to explain technical risk to

🎁 Benefits

• Shape how every career evolves in the AI economy, at global scale, with impact your friends, family
• Partner hand-in-hand with world-class AI labs, Fortune 500 partners and the world’s top educational
• Work together with engineers, scientists, operators, and more from Palantir, Meta, Scale AI, and
• Build a massive, fast-growing business with billions in revenue