Description
NVIDIA is hiring an AI Systems Software Engineer to develop production-quality software across its inference systems stack, including cuDNN, FlashInfer, GPU-accelerated deep learning primitives, LLM inference runtimes, serving abstractions, just-in-time compilation, and performance-critical runtime infrastructure. The role involves designing and optimizing kernels, software abstractions, APIs, and systems; analyzing workload performance; collaborating with deep learning, compiler, GPU architecture, and open-source teams; and contributing to inference ecosystem projects.
