Take charge of building an AI security evaluation platform as a Principal Developer. Leverage your strong software development and security systems knowledge to create tools that enhance agent robustness.
In this pivotal role, you will be integral to the AI Safety Studio, focusing on developing evaluation methodologies and infrastructure for AI agents. Collaborating with researchers and providing mentorship to junior developers will be crucial to fostering a technically sound environment. Your contributions will directly impact security evaluations and advancements in AI technologies.
Key Responsibilities:
• Build and maintain an AI agent security evaluation platform
• Implement advanced scoring and evaluation tools
• Develop comprehensive data schemas for effective testing
• Assess threat models and attack vectors
• Design policy enforcement systems for security
Requirements:
• Bachelor's or Master's in relevant fields
• 5–7 years in software development<...