Compute Architecture Software Engineer

China, ShanghaiFull-time2025-09-25 → 2026-11-11

Core

Develop and optimize software solutions to accelerate LLM inference using GPU technology for diverse computing environments.

Role type

Senior IC LLM inference software engineer

Builds

GPU-accelerated LLM inference solutions

Domain

AI / Deep Learning / GPU Computing

Deliverable

production ML models

Required skills

GPU programming, LLM inference, Python, C++, CUDA, deep learning frameworks

Technologies

CUDA, Python, C++

Apply with CareerPlan

Free — create an account and upload your CV once; you approve before anything is sent.

See similar → See original on Workday ↗

About NVIDIA

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to

Job-hunting on the side?

Upload your CV once — CareerPlan prepares applications to roles like this, you approve them in one click, and we send them and track every reply.

Start with your CV →