Microsoft's Artificial Intelligence Performance team is looking to optimize the performance of AI software, specifically Large Language Models (LLMs) like those from OpenAI, to run efficiently across a wide range of hardware, from supercomputers to mobile devices. This optimization is crucial for reducing hardware costs (capex goals) and enabling faster deployment of AI models in major Microsoft products and Azure services, which handle trillions of inferences daily.
Requirements
- 4+ years technical engineering experience with coding in languages including, but not limited to, C/C++, Python
- 2+ years’ practical experience working on high performance applications and performance debug and optimization on CPU's/GPU's
- Technical background and solid foundation in software engineering principles, computer architecture, GPU architecture, HW neural net acceleration
- Experience in end-to-end performance analysis and optimization of state of the art LLMs, HPC applications including proficiency using GPU profiling tools
- 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
Responsibilities
- Identify and drive improvements to end-to-end inference performance of OpenAI and other state of the art LLMs
- Measure, benchmark performance on Nvidia/AMD GPU's and first party Microsoft silicon
- Optimize and monitor performance of LLMs and build SW tooling to enable insights into performance opportunities ranging from the model level to the systems and silicon level, help reduce the footprint of the computing fleet and achieve Azure AI capex goals
- Enable fast time to market of LLMs/models and their deployments at scale by building SW tools that afford velocity in porting models on new Nvidia, AMD GPUs and Maia silicon
- Design, implement, and test functions or components for our AI/DNN/LLM frameworks and tools
- Speeding up/reducing complexity of key components/pipelines to improve performance and/or efficiency of our systems
- Communicate and collaborate with our partners both internal and external
Other
- Embody Microsoft's Culture and Values
- SF Bay Area, Redmond locations preferred, remote locations considered for strong candidates.
- An entrepreneurial approach and ability to take initiative and move fast are essential.
