Intern

This internship offers a specialized track in one of three areas: TensorRT LLM Inference Optimization, TensorRT Compiler Graph Optimization, or CuTe DSL & CUDA Kernels Development. The role focuses on building high-performance AI systems, optimizing model execution, and enhancing GPU compute kernels for deep learning operations. Interns will collaborate with framework and research teams to deliver efficient multi-GPU model serving and improve compiler optimization passes.