| Microsoft Careers

What you'll do

• Benchmark OpenAI and other LLM models for performance on GPUs and Microsoft hardware.
• Debug and optimize training/inference workloads on CPUs/GPUs for improved efficiency.
• Monitor performance regressions and drive continuous improvements in deployment time and hardware usage.
• Develop scalable, production-ready AI performance enhancements across the software stack.
• Profile state-of-the-art LLMs using GPU profiling tools to ensure optimal performance.

What we're looking for

• 6+ years of technical engineering experience with coding in C++ or Python.
• Bachelor's Degree in Computer Science or related field plus extensive relevant work experience.
• 4+ years’ hands-on experience working on high-performance applications and performance debugging/optimization for CPUs/GPUs.
• Experience with DNN/LLM inference and familiarity with DL frameworks like PyTorch, TensorFlow, ONNX Runtime, CUDA, ROCm, Triton.
• Solid foundation in software engineering principles, computer architecture, GPU architecture, and hardware neural net acceleration.
• Proficiency in end-to-end performance analysis and optimization of state-of-the-art LLMs and HPC applications using GPU profiling tools.