Principal AI Performance Engineer
$262,700 - $355,400 USD yearly
About the role
Work directly with customers across the Bay Area to optimize AI workloads running on Arm technology for performance and power efficiency. You will develop kernel level implementations across deep neural network models and use technical insights to influence Arm IP and tooling roadmaps.
What you'll do
- Develop optimized solutions for AI workloads, from kernel level to system level, to meet customer application requirements.
- Create production quality reference implementations, documentation, and performance focused technical content.
- Act as a technical bridge between customers and internal engineering teams to diagnose and resolve complex performance issues.
- Influence Arm IP and software roadmaps using insights gathered from production customer use cases.
- Present progress, technical analysis, and architectural recommendations to audiences ranging from engineers to senior leadership.
What you'll need
- Experience optimizing DNNs in Triton, CUDA, or other kernel level programming languages.
- Deep understanding of parallel computing, memory hierarchies, and performance optimization techniques for DNNs.
- Strong programming skills in Python and C++.
- Experience with modern AI frameworks, execution models, and performance profiling and analysis tools.
- Demonstrated technical communication and interpersonal skills.
Nice to have
- Experience in a customer facing or field engineering environment.
- Experience within the Arm ecosystem.
- Background in AI performance optimization for edge devices.
Skills: AI workloads, DNN models, kernel level implementations, Triton, CUDA, Arm technology
More semiconductor jobs: Arm Holdings jobs · AI chip design jobs · San Jose jobs
This role has been open 138 days — well above the 104-day median for AI/ML Hardware Engineering roles.
AI/ML Hardware Engineering · AI ML Hardware
|
Open roles in category
469
|
Median days open
104 d
|
Category median salary (all employers)
$238k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | Arm Holdings | All employers we track in this specialty (469 roles · 73 employers) |
|---|---|---|
| Open roles in this specialty | 11 | 469 |
| Open roles in the wider Software, Firmware & Systems family | 137 | 6531 · 156 employers |
| Median days open | 11 d | 104 d (−93 d vs this employer) |
| Median salary (USD postings) | — | $238k |
Skills observed across this category: AI workloads, DNN models, kernel level implementations, Triton, CUDA, Arm technology
Who's hiring in this category
- NVIDIA · 105 open roles · median 82 d
- Qualcomm · 91 open roles · median 129 d
- AMD · 29 open roles · median 122 d
- Mobileye · 15 open roles · median 96 d
- Analog Devices · 14 open roles · median 57 d
- Micron Technology · 14 open roles · median 69 d
How we counted: 469 open AI/ML Hardware Engineering (AI ML Hardware) roles from 73 employers tracked in the SemiconductorJobs index, counted 8 Nov 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.