Skip to main content

Software Engineer, LLM Inference at NVIDIA

Department: Engineer, Sys SW

Language
Setup
On-site
Location
Beijing
Level
mid
Posted

Description

NVIDIA is hiring a CPU computing engineer based in Shanghai to develop and scale robust inferencing software across multiple platforms, analyze and optimize performance, track developments in artificial intelligence, and guide machine-learning inference direction with software, research, and product teams. The role requires a master's degree or higher in a computing-related field, at least four years of relevant software development experience, strong C/C++ and software design skills, experience with PyTorch, and excellent English communication skills.

For job seekers

Ready to find a role that actually fits?

Upload your résumé, start a Job Search Thread, and let Metaintro rank real openings against your experience — then guide you from search to offer.

Match

Compare live roles against your current evidence.

Position

Turn proof projects into role-specific applications.

Improve

Use market feedback to keep the skill plan current.

Return to navigation