Senior Software Engineer, Deep Learning Inference Workflows

NVIDIA, the world leader in accelerated computing, is seeking a Senior Software Engineer for their Deep Learning Inference Workflows team. This role focuses on building state-of-the-art inference frameworks for accelerating Deep Learning models, particularly Large Language Models, on NVIDIA GPUs. The position involves developing TensorRT components, NVIDIA's SDK for high-performance deep learning inference, using C++ and Python to create graph parsers, optimizers, and deployment tools.

The ideal candidate will have 6+ years of software development experience with strong C++ skills and deep understanding of Machine Learning concepts. They'll work with deep learning experts, GPU architects, and DevOps engineers in a collaborative environment. Additional valuable skills include system software development, GPU kernel programming with CUDA or OpenCL, and experience with ML frameworks like PyTorch and TensorFlow.

NVIDIA offers a competitive compensation package with a base salary range of $184,000 - $356,500 USD, plus equity and benefits. The company is known for being one of technology's most desirable employers, fostering innovation and tackling challenging problems in AI and digital twins that transform major industries. This hybrid role, based in Santa Clara, provides an opportunity to make significant contributions to NVIDIA's success in the rapidly growing field of deep learning inference.