AI Computing Software Development Intern

NVIDIA invites skilled interns in artificial intelligence computing solutions to join our AI Compute team in Taiwan. This is your chance to work on one of the globe’s most advanced AI systems.

You will help develop technologies for Large Language Models, Recommender Systems, and Generative AI, and push the limits of GPU performance for AI inference.

As an intern, you’ll focus on one of two specialized tracks: TensorRT-LLM – Inference Optimization (Python / PyTorch) or TensorRT Compiler – Graph Optimization (C++).

For TensorRT-LLM:

• Build and enhance high-performance LLM inference pipelines on key LLM models.
• Analyze and optimize LLM model execution, scalability, and memory use.
• Collaborate across framework and research teams to deliver efficient multi-GPU model serving for Agentic AI workloads.

For TensorRT Compiler:

• Work on the TensorRT compiler backend to improve graph transformations and code generation for NVIDIA GPUs.
• Develop compiler optimization passes, refine operator fusion, and optimize memory usage.
• Collaborate with CUDA and hardware architecture teams to accelerate Deep Learning inference computations.

What we need to see:

• Pursuing a B.S., M.S., Ph.D., or equivalent in Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, or related fields.
• Excellent problem-solving ability, curiosity for modern AI systems, and passion for GPU computing and deep learning software performance.
• TensorRT-LLM: Strong Python programming and experience with PyTorch; solid understanding of underlying LLM inference operations and GPU acceleration.
• TensorRT Compiler: Proficient in C++, with experience in compiler or performance optimization.

Join us and play a part in building the AI computing platforms that drive innovation across industries worldwide.