ML Compiler Engineer - CA, San Jose, United States
Originally posted 21 October 2026 by the employer.
Target NPU hardware across Vitis-AI and Ryzen-AI using AMD's proprietary AI-engine architecture.
About the role
This software development role is in the AI group at AMD, working on compiler tools for Vitis-AI and Ryzen-AI software platforms. The role targets ML accelerator devices with NPUs based on AMD's proprietary AI-engine architecture across Client and Embedded product portfolios.
What you'll do
- Build a new compiler tool stack from the bottom up in collaboration with senior developers and domain experts. - Apply a data-driven and structured approach to analysis and optimization efforts. - Contribute to compiler algorithms, architectural design changes, and related technical solutions. - Debug, analyze, and resolve existing issues while exploring more efficient alternatives across the compiler stack. - Collaborate with geographically distributed engineering teams.
What you'll need
- Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, a related field, or equivalent. - Strong programming skills in C++. - Experience with a compilation stack targeting custom hardware accelerators. - Experience with modern source control systems such as GitHub. - Knowledge of machine learning model structures.
Nice to have
- Knowledge of MLIR and dialects. - Experience with AI agents for development or qualification tasks.
Skills: C++, compiler, MLIR, NPU, AI accelerator
This role has been open 0 days — well below the 50-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · Infrastructure Platform
|
Open roles in category
998
|
Median days open
50 d
|
Median salary
$235k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | AMD | All employers we track in this specialty (998 roles · 89 employers) |
|---|---|---|
| Open roles in this specialty | 58 | 998 |
| Open roles in the wider Software, Firmware & Systems family | 406 | 6296 · 145 employers |
| Median days open | 23 d | 50 d (−27 d vs this employer) |
| Median salary (USD postings) | — | $235k |
Skills observed across this category: C++, compiler, MLIR, NPU, AI accelerator
Who's hiring in this category
- NVIDIA · 290 open roles · median 47 d
- Qualcomm · 62 open roles · median 51 d
- AMD (this employer) · 58 open roles · median 22 d
- Graphcore · 50 open roles · median 96 d
- Intel Corporation · 44 open roles · median 13 d
- Cerebras · 35 open roles · median 86 d
How we counted: 998 open Infrastructure/Platform Software (Infrastructure Platform) roles from 89 employers tracked in the SemiconductorJobs index, counted 21 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.