2027 PhD ML System Engineering Intern/Co-op - CA, San Jose, United States
Originally posted 11 September 2026 by the employer — open 8 days.
Optimize LLM or VLM performance on the Ryzen AI NPU.
About the role
This internship/co-op involves optimizing the performance of Large Language Models (LLM) or Vision Language Models (VLM) on the Ryzen AI NPU. You will focus on analyzing and accelerating AI models on a tiled dataflow accelerator.
What you'll do
- Take an LLM or VLM and make it run faster on the Ryzen AI NPU.
- Study time and memory usage of AI models.
- Propose changes to optimize operator runtime.
- Write and tune AIE kernels with IRON to optimize GEMM, attention, normalization, and activation functions.
- Present findings to the engineering organization.
- Document learned insights for team use.
What you'll need
- Completing a PhD in Computer Science, Computer Engineering, or Electrical Engineering.
- Strong knowledge of LLM and VLM architectures: attention, KV cache, prefill versus decode, and vision encoder fusion.
- Experience with compilers: graph lowering, operator fusion, scheduling, tiling, and memory planning.
- Proficiency in Python and C++.
- Ability to profile code to identify compute-bound versus memory-bound behavior.
Nice to have
- MLIR experience.
- Familiarity with the AMD AI Engine (AIE) architecture.
- Experience writing kernels or dataflow designs with IRON.
Skills: LLM, VLM, Ryzen AI NPU, AIE kernels, transformer
This role has been open 8 days — well below the 66-day median for AI/ML Hardware Engineering roles.
AI/ML Hardware Engineering · AI ML Hardware
|
Open roles in category
517
|
Median days open
66 d
|
Median salary
$232k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | AMD | All employers we track in this specialty (517 roles · 76 employers) |
|---|---|---|
| Open roles in this specialty | 43 | 517 |
| Open roles in the wider Software, Firmware & Systems family | 389 | 5787 · 143 employers |
| Median days open | 61 d | 66 d (−5 d vs this employer) |
| Median salary (USD postings) | — | $232k |
Skills observed across this category: LLM, VLM, Ryzen AI NPU, AIE kernels, transformer
Who's hiring in this category
- Qualcomm · 106 open roles · median 98 d
- NVIDIA · 85 open roles · median 66 d
- AMD (this employer) · 43 open roles · median 61 d
- Micron Technology · 32 open roles · median 38 d
- Mobileye · 25 open roles · median 52 d
- Analog Devices · 14 open roles · median 23 d
How we counted: 517 open AI/ML Hardware Engineering (AI ML Hardware) roles from 76 employers tracked in the SemiconductorJobs index, counted 20 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.