Compiler Engineer, Hardware - Palo Alto, CA, United States
$200,000 - $420,000 USD yearly
Originally posted 15 May 2026 by the employer.
Build the compiler stack from PyTorch graphs to custom ISA assembly code using MLIR and LLVM.
About the role
As a Compiler Engineer, Hardware at River, you will build the software bridge between AI models and custom silicon. You will create the compiler stack from PyTorch graphs down to optimized custom ISA assembly code.
What you'll do
- Design and implement compiler passes to lower PyTorch models into custom hardware, leveraging MLIR dialects and LLVM frameworks. - Develop and maintain the backend toolchain for custom silicon, including instruction scheduling, register allocation, and hardware-specific code generation. - Design tiling and fusion strategies to maximize bandwidth utilization and minimize on-chip memory movement. - Collaborate with software and hardware teams to integrate high-performance kernels into the automated compiler flow. - Identify compilation gaps where the compiler fails to achieve peak hardware performance, partnering with the performance team on targeted optimizations. - Partner with RTL and Architecture teams to change custom ISA definitions.
What you'll need
- Bachelor’s degree in Electrical Engineering or Computer Engineering, and 5+ years of practical industry experience working with advanced process nodes (7nm or below). - Hands-on experience with MLIR or XLA for deep learning workloads. - Deep understanding of PyTorch internals and how they interface with external backends. - Proficiency in modern C/C++ for building compiler infrastructure. - Knowledge in Computer Architecture and programming models for SoCs, CPUs, GPUs, or AI accelerators.
Nice to have
- Hands-on experience in post-Silicon firmware and model update patches. - Experience defining and implementing custom dialects, lowering passes, and graph rewrites in an LLVM-based ecosystem. - Knowledge of the tradeoffs between static and runtime environments, including JITs and ABIs.
Skills: AI compiler, PyTorch, MLIR, LLVM, custom silicon
This role has been open 130 days — well above the 56-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
242
|
Median days open
56 d
|
Median salary
$220k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | River | All employers we track in this specialty (242 roles · 20 employers) |
|---|---|---|
| Open roles in this specialty | 2 | 242 |
| Open roles in the wider Software, Firmware & Systems family | 7 | 6298 · 144 employers |
| Median days open | 86 d | 56 d (+30 d vs this employer) |
| Median salary (USD postings) | — | $220k |
Skills observed across this category: AI compiler, PyTorch, MLIR, LLVM, custom silicon
Who's hiring in this category
- NVIDIA · 120 open roles · median 56 d
- AMD · 52 open roles · median 54 d
- Intel Corporation · 25 open roles · median 13 d
- Qualcomm · 18 open roles · median 127 d
- Arm Holdings · 5 open roles · median 120 d
- Graphcore · 4 open roles · median 2 d
How we counted: 242 open Infrastructure/Platform Software (GPU Software Stack) roles from 20 employers tracked in the SemiconductorJobs index, counted 23 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.
River
Similar Jobs
Infrastructure Systems Engineer - Arizona, Phoenix, United States
Intel Corporation · Remote friendly (US, Arizona, Phoenix, United States)
Infrastructure Storage Engineer - Arizona, Phoenix, United States
Intel Corporation · Remote friendly (US, Arizona, Phoenix, United States)