AI Computing Software Development Engineer, TensorRT-LLM

NVIDIA is seeking a Software Development Engineer to join their TensorRT-LLM team, focusing on LLM inference optimization. This role sits at the intersection of deep learning and high-performance computing, working on software that powers AI breakthroughs worldwide. The position involves developing and optimizing inference software for Large Language Models, collaborating with cross-functional teams, and contributing to the evolution of AI computing platforms. The ideal candidate will combine strong technical skills in Python, deep learning frameworks, and software engineering with an understanding of LLM architectures and inference techniques. This role offers the opportunity to work at a leading technology company that's driving innovation in AI and accelerated computing, with exposure to cutting-edge technology and the chance to influence the future of AI infrastructure. NVIDIA offers competitive compensation and benefits, fostering an inclusive environment that values diversity and innovation. The position requires both technical expertise and collaborative skills, making it ideal for someone passionate about advancing the field of AI computing.