Senior Software Engineer, LLM Inference

NVIDIA, a global leader in accelerated computing and AI technology, is seeking a Senior Software Engineer specializing in LLM Inference at their Shanghai location. This role sits at the intersection of GPU computing and artificial intelligence, focusing on developing and optimizing inference software for large language models. The position offers an opportunity to work with cutting-edge AI technology, particularly in AI-City and self-driving car applications, utilizing NVIDIA's powerful GPU-accelerated libraries including CUDA, cuDNN, and TensorRT.

The ideal candidate will join a team that's pushing the boundaries of AI implementation, working on solutions that directly impact the future of autonomous vehicles and smart cities. This role requires both technical expertise in C/C++ programming and deep learning frameworks, as well as a strong understanding of the latest developments in AI, particularly in LLMs and generative models.

NVIDIA has a rich history of innovation, from inventing the GPU in 1999 to revolutionizing parallel computing and igniting the modern AI era. The company's mission is to amplify human imagination and intelligence, making this role perfect for someone passionate about advancing AI technology and its real-world applications.

The position offers the chance to work with cross-functional teams, influence the direction of machine learning inferencing, and contribute to NVIDIA's continued leadership in AI and GPU computing. The successful candidate will be part of a company that has continuously reinvented itself and stays at the forefront of technological innovation.