Senior Software Engineer - Performance Tooling
Overview:
Skills, Experience, Qualifications, If you have the right match for this opportunity, then make sure to apply today. In this role you will optimize and quantify AI model performance across the full stack, from abstractions to APIs, on GPUs and Microsoft hardware. You’ll benchmark OpenAI and other LLMs, pinpoint bottlenecks, and drive improvements to reduce deployment time and hardware footprint. You will collaborate with researchers and engineers to deliver scalable, production-ready performance gains. This is a hands-on, impact-focused position at the intersection of AI, hardware, and software tooling.
Responsibilities:
- Work across multiple layers of the AI software stack to enable large-scale model training and inference
- Benchmark OpenAI and other LLMs for performance on GPUs and Microsoft hardware
- Debug, profile, and optimize performance for training/inference workloads on CPUs/GPUsMonitor performance regressions and drive continuous improvements to reduce time-to-deploy and hardware footprint
- Collaborate across teams of researchers and engineers to deliver scalable, production-ready AI performance improvements
Key requirements:
- Bachelor in Computer Science or related field AND 4+ years of technical engineering experience with coding in C++ or Python OR xaygatp equivalent experience
- Ability to meet Microsoft, customer and/or government security screening requirements (Cloud background check)
- Cross-team collaboration
- Independent project leadership
- Strong problem-solving and communicationDNN/LLM inference experience
- Familiarity with PyTorch, TensorFlow, or ONNX RuntimeCUDA, ROCm, Triton familiarity