Overview
Every time someone uses Azure OpenAI Service, their request needs to reach the right graphics processing unit GPU, in the right region, at the right moment. Our team makes that happen. We build the platform that decides how AI traffic flows across Microsoft's global infrastructure, so services like Azure OpenAI and Microsoft Copilot stay fast and reliable. You'll join a supportive, connected team that keeps these experiences fair and dependable for every customer while making the most of every GPU we run. As a Principal Software Engineer, AI Infrastructure on our team, you'll guide how AI requests are routed, prioritized, and matched to available computing capacity around the world. You'll shape the design of large distributed systems, work closely with partner teams across Microsoft and OpenAI, and help the engineers around you grow. This opportunity will allow you to influence the design of one of the largest AI platforms in the world, deepen your knowledge of large-scale optimization and efficiency, and grow as a trusted technical leader across many teams. 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.
Responsibilities
- Design - Own the overall design of how AI traffic and computing capacity are managed across regions. Guide design reviews and help the team weigh speed, reliability, scale, and cost when making choices.
- Coding - Write and review clear, secure, well-tested code for routing, prioritization, and capacity planning. Set coding practices that other teams can reuse.
- Implement - Work with product and program managers to turn the long-term vision into a dependable, step-by-step roadmap. Use feature flags and gradual rollouts to test changes safely, measure their impact, and roll back quickly when needed.
- Reliability and Supportability - Take part in the on-call rotation as a designated responsible individual DRI for critical AI services. Lead reviews after incidents and improve monitoring so issues are caught early and happen less often.
- Understand User Requirements - Partner with product, research, and infrastructure teams to understand what customers need as new AI models and capabilities launch. Work through shared dependencies cooperatively and make sure testing and support paths are ready before launch.
- Engineering Excellence - Help keep our services secure, private, and compliant through threat modeling, safe deployment checks, and clear records. Mentor engineers and share what you learn about building reliable systems at scale.
- AI-Native Development - Help the team use artificial intelligence AI tools and agents across the software development lifecycle SDLC, from writin
