Deep Learning Software Engineer, Inference - New College Grad 2026

Design, build, and optimize GPU-accelerated deep learning inference software for large-scale model serving. Contribute to high-performance open-source inference frameworks and improve deployment and serving of language models. Work across NVIDIA accelerators (datacenter GPUs to edge SoCs) and collaborate with teams to deliver performance optimization, scaling, and new features in NVIDIA inference libraries, including vLLM and SGLang.