AI Computing Software Development Intern - 2027

Responsibilities

• As an intern, you’ll focus on one of three specialized tracks
• TensorRT LLM – Inference Optimization (Python / PyTorch)
• Build and enhance high‐performance LLM inference pipelines.
• Analyze and optimize model execution, scalability, and memory usage.
• Collaborate across framework and research teams to deliver efficient multi‐GPU model serving.
• TensorRT Compiler – Graph Optimization (C++): Work on the TensorRT compiler backend to improve graph transformations and code generation for NVIDIA GPUs.
• Develop compiler optimization passes, refine operator fusion and memory allocation, and collaborate with CUDA and hardware architecture teams.
• CuTe DSL & CUDA Kernels Development / Optimization (CUDA C++ / Python DSL)
• Design and tune GPU compute kernels and DSL implementations for core deep learning operations such as GEMM, MoE, Attention and Convolution. Profile, analyze and improve CUDA kernel performance to achieve maximum GPU efficiency.
• What We need to see

Languages