At Youth Works Hub, we reviewed this AI Computing Software Development Intern position at NVIDIA in Taipei, Taiwan. NVIDIA invites skilled interns in artificial intelligence computing solutions to join its AI Compute team in Taiwan. Interns focus on one of two tracks, TensorRT-LLM Inference Optimization or TensorRT Compiler Graph Optimization, and the listing has no deadline.
About the Role
This is a chance to work on one of the globe's most advanced AI systems. You help develop technologies for Large Language Models, Recommender Systems and Generative AI, and push the limits of GPU performance for AI inference.
Two Specialized Tracks
As an intern, you focus on one of two specialized tracks: TensorRT-LLM, Inference Optimization (Python / PyTorch), or TensorRT Compiler, Graph Optimization (C++).
TensorRT-LLM
๐๏ธ Build and enhance high-performance LLM inference pipelines on key LLM models.
๐ Analyze and optimize LLM model execution, scalability and memory use.
๐ค Collaborate across framework and research teams to deliver efficient multi-GPU model serving for Agentic AI workloads.
TensorRT Compiler
๐งฑ Work on the TensorRT compiler backend to improve graph transformations and code generation for NVIDIA GPUs.
๐ง Develop compiler optimization passes, refine operator fusion and optimize memory usage.
โก Collaborate with CUDA and hardware architecture teams to accelerate Deep Learning inference computations.
What NVIDIA Needs to See
๐ Pursuing a B.S., M.S., Ph.D. or equivalent in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics or related fields.
๐งฉ Excellent problem-solving ability, curiosity for modern AI systems, and passion for GPU computing and deep learning software performance.
๐ TensorRT-LLM: strong Python programming and experience with PyTorch, plus a solid understanding of underlying LLM inference operations and GPU acceleration.
๐ ๏ธ TensorRT Compiler: proficiency in C++, with experience in compiler or performance optimization.
NVIDIA invites you to play a part in building the AI computing platforms that drive innovation across industries worldwide. NVIDIA is an equal opportunity employer and ensures that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process.
Youth Works Hub lists this NVIDIA internship among the current internship opportunities in Taiwan.
Frequently Asked Questions
Which tracks does the NVIDIA AI Computing internship offer?
TensorRT-LLM Inference Optimization (Python / PyTorch) and TensorRT Compiler Graph Optimization (C++). Interns focus on one of the two.
Who can apply?
Students pursuing a B.S., M.S., Ph.D. or equivalent in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics or related fields.
Which programming skills are needed?
For TensorRT-LLM, strong Python and experience with PyTorch. For TensorRT Compiler, proficiency in C++ with experience in compiler or performance optimization.
What will I work on?
Technologies for Large Language Models, Recommender Systems and Generative AI, pushing the limits of GPU performance for AI inference.
Where is the internship based?
In Taipei, Taiwan, within NVIDIA's AI Compute team.
Deadline
โณ As soon as possible!







