Performance Software Intern, Deep Learning Libraries - 2027
Originally posted 23 September 2026 by the employer.
This position primarily deals with code lower in the deep learning software stack, right down to the GPU HW.
About the role
You will contribute to the underlying software that powers artificial intelligence, with a focus on peak GPU efficiency and code lower in the deep learning software stack, down to the GPU HW.
What you'll do
- Write highly tuned compute kernels for core deep learning operations (e.g., matrix multiplies, MoE, Attention).
- Follow general software engineering best practices, including support for regression testing and CI/CD flows.
- Collaborate with compiler teams on generating optimal assembly code.
- Collaborate with deep learning training and inference performance teams on optimization needs.
- Collaborate with hardware and architecture teams on programming models for new deep learning hardware features.
- Identify bottlenecks, optimize resource utilization, and improve throughput.
What you'll need
- Pursuing a Master's or PhD degree in Computer Science, Computer Engineering, Applied Math, or a related field.
- Demonstrated strong programming and software design skills, including debugging, performance analysis, and test design.
- Experience with performance-oriented parallel programming (e.g., with OpenMP or pthreads).
- Solid understanding of computer architecture and some experience with assembly programming.
Skills: optimized code, deep learning operations, NVIDIA GPUs, compute kernels, CUDA
This role has been open 0 days — well below the 49-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
221
|
Median days open
49 d
|
Median salary
$221k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | NVIDIA | All employers we track in this specialty (221 roles · 19 employers) |
|---|---|---|
| Open roles in this specialty | 116 | 221 |
| Open roles in the wider Software, Firmware & Systems family | 1001 | 5948 · 143 employers |
| Median days open | 47 d | 49 d (−2 d vs this employer) |
| Median salary (USD postings) | — | $221k |
Skills observed across this category: optimized code, deep learning operations, NVIDIA GPUs, compute kernels, CUDA
Who's hiring in this category
- NVIDIA (this employer) · 109 open roles · median 47 d
- AMD · 57 open roles · median 43 d
- Qualcomm · 20 open roles · median 118 d
- Intel Corporation · 9 open roles · median 41 d
- Arm Holdings · 5 open roles · median 90 d
- Bolt Graphics · 3 open roles · median 49 d
How we counted: 221 open Infrastructure/Platform Software (GPU Software Stack) roles from 19 employers tracked in the SemiconductorJobs index, counted 23 Sept 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.