Principal Engineer, Teams Agents & SDK
 Microsoft | |
 United States, Washington, Redmond | |
 Jul 02, 2025 | |
|
OverviewMicrosoft Teams is a hub for collaboration, facilitating interaction between people and intelligent agents. The focus is on creating building-blocks for Agents in Teams to support human-AI cooperation. It serves both internal and external developers. We are seeking a Principal Engineer, Teams Agent & SDK. The mission includes:Enabling Teams Agents creation with the AI SDK: Assisting developers in building agents with the Teams AI SDK. Check out our exciting new SDK:https://aka.ms/teamslib Delivering the Agent Accelerator: Providing open-source starter agents to streamline innovation with agents. Check out our collection of Pre-Built Agents: https://aka.ms/teams-agentsWe develop in (and for) Python, C#, and TypeScript, leveraging both open-source and Microsoft technologies for maximum flexibility and impact. We may expand to other languages in the future.If you care deeply about developer experience and are passionate about crafting tools that make it easier for developers to build GenAI Agents in this fast-evolving industry, we invite you to join us on this journey. Tackle complex technology challenges with global impact and help shape the future of human-AI collaboration! Microsoft's mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.
ResponsibilitiesAdvance one or both missions: a) Facilitate the creation of Teams (SDK) Agents. b) Develop compelling Teams Agents that inspire others to create their own.Support technical vision and architecture for the Teams AI SDK components and opensource Agent Accelerator templates and libraries, marrying conversational UX with distributed, cloudnative patterns.Define data, API, and messaging contracts across TypeScript, C#, and Python stacks to keep client, service, and LLM inference layers loosely coupled yet cohesive.Prototype emerging OSS tools and LLM capabilities, validating architecture decisions with PoCs and load tests before production rollout.Mentor and unblock engineers, providing architectural reviews, threat models, and bestpractice guidance for distributed systems and conversational AI.Define lightweight, secure protocols for agenttouser and agenttoagent messaging-covering envelopes, capability negotiation, shared context, and escalation paths. | |