Principal Software Development Engineer - CA, Santa Clara, United States
Originally posted 8 September 2026 by the employer.
Optimize collective communication primitives on GPU accelerators.
About the role
This role involves leading strategic software engineering efforts to improve the performance of key applications and benchmarks, working with the latest hardware and software technology.
What you'll do
- Work with strategic customers to understand requirements and identify opportunities for AMD hardware and software.
- Close gaps in the AMD software stack to support customer solutions.
- Optimize collective communication primitives on GPU accelerators (NCCL/RCCL).
- Develop alongside customers to drive projects from proof of concept to production.
- Translate customer needs and insights into actionable feedback for AMD's AI roadmap.
- Use Agentic AI to enhance productivity, automate workflows, and improve operational efficiency.
- Apply a data-minded approach to target optimization efforts.
What you'll need
- Strong programming skills in C/C++ and Python.
- Experience with GPU kernel programming using CUDA or HIP.
- Expertise with modern LLM serving frameworks (e.g., vLLM, SGLang).
- Experience in implementing and optimizing attention and KV-cache primitives on GPU accelerators.
- Strong performance analysis and optimization skills for both CPU and GPU.
- Experience with open-source software development, including collaboration with community maintainers.
Nice to have
- A track record of direct Client Engagement with experience working with customers to solve ambiguous technical problems.
- Experience providing clear and timely communication to the executive leadership team.
Skills: GPU kernel programming, CUDA, HIP, LLM serving frameworks, NCCL/RCCL
This role has been open 36 days — well below the 56-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
231
|
Median days open
56 d
|
Median salary
$236k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | AMD | All employers we track in this specialty (231 roles · 20 employers) |
|---|---|---|
| Open roles in this specialty | 53 | 231 |
| Open roles in the wider Software, Firmware & Systems family | 404 | 6136 · 145 employers |
| Median days open | 64 d | 56 d (+8 d vs this employer) |
| Median salary (USD postings) | — | $236k |
Skills observed across this category: GPU kernel programming, CUDA, HIP, LLM serving frameworks, NCCL/RCCL
Who's hiring in this category
- NVIDIA · 117 open roles · median 55 d
- AMD (this employer) · 53 open roles · median 65 d
- Qualcomm · 19 open roles · median 106 d
- Intel Corporation · 17 open roles · median 6 d
- Arm Holdings · 5 open roles · median 112 d
- d-Matrix · 2 open roles · median 120 d
How we counted: 231 open Infrastructure/Platform Software (GPU Software Stack) roles from 20 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.