Research Engineer, Agentic Safety

As a Research Engineer in Strategic Initiatives, you will use your AI and software engineering expertise to collaborate with domain experts and other machine learning scientists within our strategic initiatives programs. Your primary focus will be on building technologies to make AI agents safer. AI agents are increasingly used in sensitive contexts with powerful capabilities, having abilities to access personal data, confidential enterprise data and code, interact with third party applications or websites, or write and execute code in order to fulfil user tasks. Ensuring that such agents are reliable, secure and trustworthy is a  large scientific and engineering challenge, with huge potential impact. In this role, you will serve this mission by building infrastructure, researching new approaches to agentic safety, building prototypes and demos, working with partner and client teams, and most importantly, land transformative impact for GDM , our product partners, and the AI ecosystem more broadly

Key responsibilities:

• Develop frameworks to evaluate the safety, security and privacy of agentic AI systems at scale across key usecases at Google and GDM
• Work on agent orchestration prototypes combining multiple AI components to reliably solve complex tasks in nuanced scenarios
• Build leaderboards and evaluation metrics for the project to hill-climb
• Integrate novel agentic technologies into research prototypes 
• Work with product teams to gather research requirements and consult on the deployment of research-based solutions to help deliver value incrementally
• Amplify the impact by generalizing solutions into reusable libraries and frameworks for privacy preserving AI agents across Google, and by sharing knowledge through design docs, open source, or external blog posts