About the job
About Glean:
Founded in 2019, Glean is an innovative AI-driven knowledge management platform that empowers organizations to efficiently find, organize, and disseminate information across their teams. By seamlessly integrating with tools such as Google Drive, Slack, and Microsoft Teams, Glean ensures that employees have access to the right information at the right time, enhancing productivity and collaboration. Our advanced AI technology streamlines knowledge discovery, allowing teams to leverage their collective intelligence more effectively.
Born from the vision of Founder & CEO Arvind Jain, Glean addresses the challenges employees face in navigating fragmented knowledge and numerous SaaS tools that hinder productivity. With a mission to create a better solution, Glean has evolved into the leading Work AI platform, combining enterprise-grade search capabilities, an AI assistant, and robust application and agent-building features that fundamentally transform how employees engage with their work.
About the Role:
As a member of the Agents Runtime team, you will contribute to the development of low-latency, reliable, and secure systems that underpin Glean's AI agents and assistant experiences at scale. Your responsibilities will include designing and managing core runtime services for multi-turn orchestration, tool integration, model routing, memory management, streaming, and safety protocols. Collaborating across distributed systems, production observability, and machine learning infrastructure integrations, you will deliver an experience that feels instantaneous, accurate, and trustworthy, all while optimizing costs and enhancing reliability.
Your Responsibilities:
- Take ownership of significant runtime challenges from architecture and design through to production launch and ongoing reliability.
- Develop and refine core services for session management, streaming responses (e.g., gRPC/WebSockets), structured tool execution, memory/state management, and policy implementation.

