Principal Software Engineer

Key details

Full job description

Microsoft is hiring a Principal Software Engineer to develop GPU-accelerated techniques for large language models and deep learning to improve Microsoft's online advertising platforms. The role involves designing and implementing inferencing capabilities, building reusable frameworks, optimizing inference performance on GPUs, collaborating with teams to enhance model deployment, and developing AI lifecycle tools. Candidates must have a Bachelor's degree in Computer Science or related field with 6+ years of engineering experience coding in C, C++, C#, Java, JavaScript, or Python, or equivalent experience. Preferred qualifications include a Master's degree with 8+ years experience or Bachelor's with 12+ years, 2+ years working with deep learning frameworks (PyTorch, OnnxRuntime, Tensorflow, vLLM, TensorRT-LLM), experience in system design, MLOps, GPU architecture, kernel programming, model quantization, Docker, Kubernetes, and technical leadership skills. The position is full-time, on-site in Redmond, Washington, with a salary range of $142,800 to $274,800 annually in most U.S. locations, higher in SF Bay Area and NYC. Candidates must pass Microsoft Cloud background checks.