Senior Software Engineer (GPU Performance)

The Artificial Intelligence (AI) Frameworks team at Microsoft develops the AI software used to train and deploy the world’s most advanced AI models. We collaborate with our hardware teams and partners to build the software stacks for Microsoft’s next-generation supercomputers and the new Maia-100 AI accelerator.  We work closely with ML researchers and developers to optimize and scale out model training and inference.  We work directly with OpenAI on the models hosted on the Azure OpenAI service.

We are hiring a Senior Software Engineer (GPU Performance) to work on GPU performance analysis and optimization.  As a member of this team, you will have the opportunity to work on the fundamental abstractions, programming models, runtimes, libraries and APIs to enable large scale training and inferencing of models on novel AI hardware.

This is a technical role focused on performance analysis and optimization of machine learning models: it requires hands-on software development skills. We’re looking for someone who has a demonstrated history of solving hard technical problems and is motivated to tackle the hardest problems in building a full end-to-end AI stack.  An entrepreneurial approach and ability to take initiative and move fast are essential.

We do not just value differences or different perspectives. We seek them out and invite them in so we can tap into the collective power of everyone in the company. As a result, our customers are better served.

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

• Software development in C/C++, Python, and in GPU languages such as CUDA, ROCm, or Triton
• Work with cutting-edge hardware stacks and a fast-moving software stack to deliver best-of-class inference and optimal cost.
• Engage with key partners to understand and implement performance analysis and optimization for state-of-the-art LLMs and other models.
• Embody our culture and values

Qualifications

Required Qualifications:

• Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C/C++, CUDA, or ROCm
  • OR equivalent experience.
• 3+ years’ practical experience working on applications that use GPUs, experience in optimizing their performance 
• Practical Experience writing new GPU kernels, going beyond experience of GPU workloads with existing library kernels

Preferred Qualifications:

• Bachelor's Degree in Computer Science
  • OR related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C/C++, CUDA, or ROCm
  • OR Master's Degree in Computer Science or related technical field AND 2+ years technical engineering experience with coding in languages including, but not limited to, C/C++, CUDA, or ROCm
  • OR equivalent experience.
• Experience in low-level performance analysis and optimization, including proficiency using GPU profiling tools such as NVIDIA Visual Profiler, and NVIDIA Nsight Compute
• Technical background and solid foundation in software engineering principles and architecture design
• Exposure to Deep Neural Network inference and experience in one or more deep learning frameworks such as PyTorch, Tensorflow, or ONNX Runtime
• Cross-team collaboration skills and the desire to collaborate in a team of researchers and developers