Senior Software Engineer - Performance | Microsoft Careers

What you'll do

• Identify and drive improvements for end-to-end inference performance of LLM models.
• Benchmark performance on Nvidia/AMD GPUs and Microsoft hardware silicon.
• Optimize and monitor performance of large language models across various levels.
• Build software tools to enable rapid deployment of models on new GPUs.
• Design, implement, and test components for AI/DNN/LLM frameworks and tools.
• Reduce complexity in key system pipelines to enhance overall efficiency.

What we're looking for

• Proven experience in end-to-end performance analysis and optimization of state-of-the-art LLMs.
• Solid foundation in software engineering principles, computer architecture, GPU architecture, and HW neural net acceleration.
• Proficiency using GPU profiling tools for benchmarking and optimizing AI models on GPUs and Microsoft hardware.
• Experience with DNN/LLM inference and familiarity with DL frameworks like PyTorch, TensorFlow, or ONNX Runtime.
• Ability to design, implement, and test functions or components for AI/DNN/LLM frameworks and tools.
• Strong cross-team collaboration skills and a track record of working effectively in interdisciplinary teams.