jobs

AI Computing Software Development Intern, LLM Inference - 2027

We are now looking for a Software Development Engineer to help TensorRT LLM and TensorRT Edge LLM projects! NVIDIA is hiring software engineers for its AI Computing team. Academic and commercial groups around the world are using GPUs to pow

In inglese

Company

NVIDIA

Location

China, Shanghai; China, Beijing

Status

Open

Posted

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

NVIDIA's AI Computing team is hiring a software development intern for its TensorRT LLM and TensorRT Edge LLM projects, based in Shanghai or Beijing and working on-site full-time. The intern builds and scales inferencing software across platforms, does performance analysis, optimization and tuning, feeds results into architecture and hardware decisions, and collaborates with software, research and product teams. The posting seeks a Master's or higher student in a computing field with strong C/C++ skills, experience with TensorFlow or PyTorch, and awareness of LLM and generative model developments.