AI Computing Software Intern, GPU Kernel Libraries - 2027

NVIDIA is hiring an AI Computing Software Intern, GPU Kernel Libraries - 2027 in Shanghai, China. Level rates it ; you can apply on NVIDIA.

Level's read on this job

Builds AI ●●●● is how Level rates this role: the job is building AI systems.
Tools and skills the posting cites include Cublas, Tensorrt and Cudnn.
Level classifies it as an internship.
Level lists 2,800+ other open roles at NVIDIA.

AI in this role

Compute and deep learning architecture optimization intern to develop high-performance operators for GPU libraries.

CublasTensorrtCudnnCusparseCutensorCPythonLlvmMlirCUDA

deep-learninggpu-kernelsperformance-optimizationcomputer-architecture

We are now looking for Compute/DL Architecture Performance Optimization Interns in our group! Are you passionate about exploring computer architectures for deep learning? Do you enjoy working at the intersection of hardware and software? NVIDIA is looking for world-class programmers and performance architects who like to continuously explore and mine the ultimate performance of each operator (or fusion operator) in deep learning networks, design and develop scalable modular infrastructure that can ship these highly optimized operators to different NVIDIA software libraries for training and inference.

What you'll be doing:

Develop high performance operators on NVIDIA GPUs for cuBLAS, TensorRT, cuDNN, cuSparse and cuTensor libraries
Analyze the performance of various GPU kernels on existing/new architecture, identify bottlenecks and propose creative solutions to improve them
Design and develop software for kernel authoring and shipping
Adopt cutting-edge AI technologies in GPU kernel or similar development workflow

What we need to see:

Pursuing a B.S., M.S., or PhD degree in computer science (or similar)
Strong programming skills in C/C++ and Python development
Familiar with GPU programming model and CUDA
Good understanding about compiler technologies and experience with LLVM and MLIR
Excellent problem solving skills, good communication and teamwork

NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!

How we rate this

AI Computing Software Intern, GPU Kernel Libraries - 2027 at NVIDIA rates 80 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.

Classification

Builds AI. The job is building AI systems.

●●●● Builds AI80 to 100
●●●○ Works on AI60 to 79
●●○○ Uses AI40 to 59
●○○○ Little AI0 to 39

Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.

Key facts

AI Computing Software Intern, GPU Kernel Libraries - 2027 is an open job at NVIDIA.
Level rates this role AI Level 4 of 4: Builds AI.
The role is based in China, Shanghai.
The job was posted on September 23, 2026.
Seniority: intern.
Applications are handled by NVIDIA. Apply on NVIDIA

Prepare for this job

Built from this posting and from similar jobs on Level.

Skills and AI tools this role asks for

Deep learningGPU KernelsPerformance OptimizationComputer ArchitectureCublasTensorrtCudnnCusparse

Questions you could be asked

Tell me about a project where deep learning was part of your work. What did you do?
Tell me about a project where gpu kernels was part of your work. What did you do?
Tell me about a project where performance optimization was part of your work. What did you do?
Tell me about a project where computer architecture was part of your work. What did you do?
Walk me through how you've used Cublas in your day-to-day work.

Adapt your resume

List these exact terms on your resume: Deep learning, GPU Kernels, Performance Optimization, Computer Architecture, and Cublas. An applicant tracking system matches the wording, not the idea.
Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.

Get your CV reviewed before you apply

Send your CV and the role you want next. Your review arrives by email within 3 days.

Get a free CV review Check your resume with the ATS resume checker