Software Engineer, LLM Inference

China, ShanghaiFull Time$70K – $140K/yr NLP

LLM inferenceNLPsoftware engineeringTensorRT-LLM

Job Description

This Shanghai software engineering role focuses on inference for large language models. The position applies NVIDIA accelerated-computing technologies to improve performance of modern language-model workloads.

Opens the verified employer application page.

Job Details

Posted: September 10, 2026
Expires: October 10, 2026
Views: 2
Applies: 0

About the Company

NVIDIA

Santa Clara, CA

NVIDIA is a technology company working on AI and machine learning solutions.

Software Engineer, LLM Inference

NVIDIA