jobs

AI Computing Development Intern, TensorRT-LLM - 2027

We are now looking for a TensorRT-LLM Software Development Engineering intern!NVIDIA is hiring software engineers for its AI Computing team. Academic and commercial groups around the world are using GPUs to power a revolution in deep learni

In inglese

Company

NVIDIA

Location

China, Shanghai

Status

Open

Posted

2026-09-23T00:00:00+00:00

An internship on NVIDIA's AI Computing team in Shanghai, working on TensorRT-LLM, the company's library for running large language models on GPUs. The intern writes and scales inference software, profiles and tunes performance, follows academic work in deep learning, and feeds findings back into architecture and hardware decisions. The posting asks for a master's degree in progress or higher, strong C/C++ and debugging skills, experience with TensorFlow or PyTorch, and English communication. Results are expected to be publishable at scientific conferences.