GPU Kernel Development Engineer - Fellow - TX, Austin, United States
Originally posted 3 September 2026 by the employer.
Drive performance for ROCm core software.
About the role
You will play a pivotal role in GPU architecture feature design, usage, API design, optimization, and deployment.
What you'll do
- Perform external benchmarking and research to define opportunities to improve GPU kernel performance on AMD machine learning products.
- Analyze and optimize the performance of GPU kernels, providing insight on optimization paths across the AI software stack.
- Partner with customers and hyperscalers to understand their unique workload requirements and deliver tailored architectural wins and software optimizations.
- Collaborate across hardware architecture, compiler, and framework teams to influence future silicon features based on evolving AI workload trends.
- Communicate and collaborate with technical experts across AMD and with partners and customers to improve ROCm applications, libraries, and tools, as well as hardware.
What you'll need
- Broad and deep experience in compute and machine learning software development.
- Experience in GPU architecture feature design, usage, API design, optimization, and deployment.
- Experience optimizing GPU kernels with advanced algorithms across the AI software stack.
- Strong GPU architecture knowledge, performance analysis, algorithm development, and machine learning experience.
Nice to have
- Strong understanding of modern model architectures (Transformer, Attention, KV Cache) and optimization techniques like quantization, speculative decoding, and FlashAttention.
- Demonstrated ability to drive cross-functional initiatives.
- Bachelor’s or Master's or PhD degree in Computer Science, Computer Engineering, or equivalent.
This role has been open 42 days — well below the 61-day median for Systems Software Engineering roles.
Systems Software Engineering · Systems Software
|
Open roles in category
689
|
Median days open
61 d
|
Median salary
$217k
|
See the full market breakdown ▾Category comparison, and who else is hiring
| Metric | AMD | All employers we track in this specialty (689 roles · 72 employers) |
|---|---|---|
| Open roles in this specialty | 63 | 689 |
| Open roles in the wider Software, Firmware & Systems family | 404 | 6135 · 145 employers |
| Median days open | 51 d | 61 d (−10 d vs this employer) |
| Median salary (USD postings) | — | $217k |
Who's hiring in this category
- Qualcomm · 166 open roles · median 78 d
- NVIDIA · 137 open roles · median 47 d
- AMD (this employer) · 64 open roles · median 50 d
- Mobileye · 28 open roles · median 74 d
- Broadcom · 21 open roles · median 51 d
- Arm Holdings · 20 open roles · median 112 d
How we counted: 689 open Systems Software Engineering (Systems Software) roles from 72 employers tracked in the SemiconductorJobs index, counted 15 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.