Principal Software Engineer - Performance Tooling

The Artificial Intelligence (AI) Frameworks team at Microsoft develops AI software that enables running AI models everywhere, from world’s fastest AI supercomputers, to servers, desktops, mobile phones, internet of things (IoT) devices and internet browsers. We collaborate with our hardware teams and partners, both internal and external, and operate at the intersection of AI algorithmic innovation, purpose-built AI hardware, systems, and software. We are a team of highly capable and motivated people that pride themselves on a collaborative and inclusive culture.  We own inference performance of OpenAI and other state of the art large language model (LLM) models and work directly with OpenAI on the models hosted on the Azure OpenAI service serving some of the largest workloads on the planet with trillions of inferences per day in major Microsoft products, including Office, Windows, Bing, SQL Server, and Dynamics.    As a Principal Software Engineer - Performance Tooling on the team, you will have the opportunity to work on multiple levels of the AI software stack, including the fundamental abstractions, programming models, compilers, runtimes, libraries and application programming interfaces (APIs) to enable large scale training and inferencing of models. You will benchmark OpenAI and other LLM models for performance on graphics processing units (GPUs) and Microsoft hardware, debug and optimize performance, monitor performance and enable these models to be deployed in the shortest amount of time and the least amount of hardware possible helping achieve Microsoft Azure's capex goals.   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.

Work across multiple layers of the AI software stack (abstractions, programming models, compilers, runtimes, libraries, and APIs) to enable large-scale model training and inference. Benchmark OpenAI and other LLMs for performance on Graphic Processing Units (GPUs) and Microsoft hardware. Debug, profile, and optimize performance for training/inference workloads on CPUs (Central Processing Units)/GPUs. Monitor performance regressions and drive continuous improvements to reduce time-to-deploy and hardware footprint. Collaborate across teams of researchers and engineers to deliver scalable, production-ready AI performance improvements.

Required/Minimum Qualifications: • Bachelor's Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C++, or Python OR equivalent experience.   Other Requirements: • Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. This includes passing the Microsoft Cloud background check upon hire/transfer and every two years thereafter.   Preferred/Additional Qualifications: Master's Degree in Computer Science or related technical field AND 12+ years technical engineering experience with coding in languages including, but not limited to, C++, or Python OR Bachelor's Degree in Computer Science or related technical field AND 15+ years technical engineering experience with coding in languages including, but not limited to, C++, or Python OR equivalent experience. 4+ years’ practical experience working on high performance applications and performance debugging and optimization on CPUs/GPUs. Experience in DNN/LLM inference and experience in one or more DL frameworks such as PyTorch, Tensorflow, or ONNX Runtime and familiarity with CUDA, ROCm, Triton. Technical background and solid foundation in software engineering principles, computer