Description
NVIDIA is hiring AI Computing Software Development Interns in Taiwan to work on large-language-model, recommender-system, and generative-AI technologies while optimizing GPU performance for AI inference. Interns may join the TensorRT-LLM track, focusing on Python and PyTorch-based LLM inference pipelines, or the TensorRT Compiler track, focusing on C++ compiler optimization, graph transformations, and GPU code generation. The role requires a computer science, computer engineering, electrical engineering, applied mathematics, or related degree in progress, along with strong problem-solving skills and experience in the relevant programming and optimization area.
