Senior Software Engineer, Deep Learning Inference

NVIDIA, the world leader in accelerated computing, is seeking a Senior Software Engineer to join their Deep Learning Inference team. This role presents an exciting opportunity to make a significant impact in the field of Deep Learning by developing state-of-the-art inference frameworks for Large Language Models (LLMs) on NVIDIA GPUs.

The position involves working with TensorRT-LLM, NVIDIA's premier library for optimizing LLM inference performance. You'll be at the forefront of AI technology, collaborating with diverse teams of deep learning experts, GPU architects, and DevOps engineers, while also engaging with the broader deep learning community through open-source development.

The ideal candidate brings 6+ years of software development experience, strong Python skills, and a deep understanding of Machine Learning concepts, particularly in Large Language Models. Experience with C++, open-source development, and frameworks like vLLM, TensorRT, PyTorch, or JAX would be highly valuable. The role offers a competitive base salary range of $184,000 - $287,500 USD, plus equity and benefits.

NVIDIA's culture emphasizes creativity, autonomy, and technical innovation. As part of one of technology's most desirable employers, you'll help build the computing platforms driving success in AI and deep learning. The company is committed to diversity and inclusion, fostering an environment where all employees can thrive and contribute to solving challenges no one else can tackle.

Located in Santa Clara, CA, with a hybrid work arrangement, this position offers the opportunity to work with cutting-edge technology while contributing to NVIDIA's mission of transforming the world's largest industries through AI and digital twins. If you're passionate about deep learning, software optimization, and want to work with some of the industry's brightest minds, this role presents an exceptional opportunity to advance your career while making meaningful contributions to the field.