CareerPlan

AI Computing Software Development Intern - 2027

China, ShanghaiInternship2026-09-23 → 2026-11-16

Core

Build and optimize high-performance AI inference pipelines, GPU compilers, and compute kernels for NVIDIA GPUs.

Role type

AI computing software development intern

Builds

High-performance LLM inference pipelines, TensorRT compiler backends, and optimized GPU compute kernels

Domain

AI computing, GPU acceleration, deep learning systems

Deliverable

production ML models

Required skills

Python, PyTorch, C++, CUDA, compiler optimization, GPU architecture, performance profiling

Preferred skills

Experience with TensorRT, LLVM, MLIR, GEMM, MoE, Attention, Convolution operations

Technologies

TensorRT, PyTorch, CUDA, C++, Python, LLVM, MLIR

Responsibilities

Build and enhance high-performance LLM inference pipelines; Develop compiler optimization passes and refine operator fusion; Design and tune GPU compute kernels for core deep learning operations

Seniority

Intern