GPU Compiler LLVM Backend Intern - 2027 - Shanghai, China
Originally posted 6 October 2026 by the employer.
The Compiler team is responsible for constructing and emitting GPU machine instructions for CUDA, PTX, OpenCL, and Fortran/C++.
About the role
This role involves working as an intern within the GPU Software organization, contributing to the development of a GPU compiler and assembler. You will contribute to constructing and emitting GPU machine instructions for Graphics (OpenGL, Vulkan, DX) and Compute (CUDA, PTX, OpenCL, Fortran, C++).
What you'll do
- Understand, modify, and improve an NVIDIA GPU compiler and assembler written in C++.
- Design and develop new compiler passes and optimizations.
- Work with global compiler, hardware, and application teams.
- Be part of a team focused on deep-learning compiler technology spanning architecture design and support through functional languages.
What you'll need
- Pursuing a B.S. or higher degree in Computer Science/Engineering.
- Excellent hands-on C++ programming skills.
- Strong background in software engineering principles.
- Good communication and documentation skills.
Nice to have
- Masters or PhD with compiler code generation experience.
- Experience in developing CUDA, DirectX, OpenGL/Vulkan applications.
- Experience in performance analysis and compile time analysis tools.
- Exposure to various ML techniques.
Skills: GPU compiler, LLVM backend, machine instructions, CUDA, parallel computing
This role has been open 0 days — well below the 56-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
225
|
Median days open
56 d
|
Median salary
$236k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | NVIDIA | All employers we track in this specialty (225 roles · 19 employers) |
|---|---|---|
| Open roles in this specialty | 127 | 225 |
| Open roles in the wider Software, Firmware & Systems family | 971 | 5996 · 146 employers |
| Median days open | 49 d | 56 d (−7 d vs this employer) |
| Median salary (USD postings) | — | $236k |
Skills observed across this category: GPU compiler, LLVM backend, machine instructions, CUDA, parallel computing
Who's hiring in this category
- NVIDIA (this employer) · 122 open roles · median 52 d
- AMD · 57 open roles · median 55 d
- Qualcomm · 17 open roles · median 165 d
- Arm Holdings · 5 open roles · median 103 d
- Intel Corporation · 5 open roles · median 53 d
- d-Matrix · 2 open roles · median 111 d
How we counted: 225 open Infrastructure/Platform Software (GPU Software Stack) roles from 19 employers tracked in the SemiconductorJobs index, counted 6 Oct 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there — it is counted in the wider Software, Firmware & Systems family row. Figures refresh nightly.