← All roles

AI Computing Software Development Engineer, TensorRT-LLM

NVIDIA· Architect
Apply on company site
Taiwan, Taipei, Taiwan, Hsinchufull-timePosted 2mo ago

About the role

Software Development Engineer for LLM inference on the TensorRT-LLM team, focused on building scalable inference software, optimizing performance for LLM inference, and collaborating across software, research, and product teams.

Responsibilities

  • Craft and develop robust inference software that can be scaled to multiple platforms for functionality and performance
  • Performance analysis and optimization for Large Language Model (LLM) inference
  • Closely follow academic and industrial developments in the field of artificial intelligence and feature update TensorRT-LLM
  • Implement kernels and runtime features to support new LLM models and inference algorithms
  • Provide feedback into the architecture and hardware design and development
  • Collaborate across the company to guide the direction of deep learning inference, working with software, research and product teams

Qualifications

  • Master or higher degree in Computer Engineering, Computer Science, Applied Mathematics or related computing focused degree (or equivalent experience)
  • 3+ years of relevant software development experience
  • Excellent Python programming skills, software design, and software engineering skills
  • Awareness of the latest developments in LLM architectures and LLM inference techniques
  • Experience working with deep learning frameworks like PyTorch and HuggingFace
  • Proactive and able to work without supervision
  • Excellent written and oral communication skills in English

Skills

Required:Python
Nice to have:C/C++CUDA/OpenCL
Last updated Aug 14, 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

More open roles at NVIDIA