← All roles

Compute Architecture Software Engineer

NVIDIA· Architect
Apply on company site
Shanghai, ChinaFull-timePosted 7mo ago

About the role

LLM Inference Software Engineer role at NVIDIA focused on accelerating LLM inference using GPU technology within the TRTLLM project, spanning from single PCs to large GPU clusters.

Responsibilities

  • Develop and optimize software solutions to accelerate LLM inference using GPU technology.
  • Collaborate with engineers to implement and refine GPU-based algorithms.
  • Analyze and determine effective methods to improve performance across diverse computing environments.
  • Engage in individual and team projects to contribute to NVIDIA's AI leadership.
  • Work in an empowering and inclusive environment to implement groundbreaking AI solutions.

Qualifications

  • 5+ years of software engineering experience, especially in GPU programming and LLM inference.
  • Proficiency in Python, C++, and CUDA.
  • Solid understanding of deep learning frameworks and techniques.
  • Strong problem-solving skills and ability to work collaboratively in a team.
  • Ambitious, initiative-taking mindset with track record of delivering results.
  • BS or above in Computer Science, Engineering, or related field, or equivalent experience.

Skills

Required:GPU programming

Benefits

  • Widely considered to be one of the technology world’s most desirable employers, NVIDIA offers highly competitive salaries and a comprehensive benefits package.
  • www.nvidiabenefits.com/
Last updated Jul 3, 2026. Interested? Apply on the company site.

About NVIDIA

World Leader in AI Computing

NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.

AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
Company profileWebsite

More open roles at NVIDIA