Senior Staff Compiler Software Engineer - CA, San Jose, United States
Originally posted 14 July 2026 by the employer. Relisted by the employer on 16 July 2026.
Develop and optimize MLIR and LLVM compiler pipelines for GPU and AI compute platforms.
About the role
AMD is seeking a Senior Staff Software Engineer to lead compiler development and GPU performance optimization for AI and compute platforms. You will design compiler technologies using MLIR and LLVM, develop optimized code-generation flows, and work with GPU architecture, runtime, and AI framework teams.
What you'll do
- Design and implement compiler optimizations using MLIR and LLVM for GPU and AI workloads. - Develop compiler passes, intermediate representations, lowering pipelines, and target-specific code generation. - Optimize graph transformations, operator fusion, tiling, vectorization, memory planning, and kernel scheduling. - Analyze generated GPU code and tune kernels for compute utilization, memory bandwidth, cache efficiency, occupancy, and synchronization. - Perform end-to-end performance analysis across AI frameworks, compilers, runtimes, libraries, and GPU hardware. - Collaborate with GPU architecture teams to enable new hardware features and drive hardware-software co-design.
What you'll need
- Bachelor’s, Master’s, or Doctorate degree in Computer Science, Computer Engineering, or a related field, or equivalent industry experience. - Deep hands-on experience with MLIR, LLVM, compiler optimization, lowering, and code generation. - Strong knowledge of compiler architecture, intermediate representations, transformation passes, and optimization pipelines. - Strong understanding of GPU architecture, including parallel execution, memory hierarchy, caches, registers, synchronization, and occupancy. - Advanced C/C++ skills with experience in HIP, CUDA, or similar GPU programming models. - Proven experience profiling and optimizing GPU kernels or compute-intensive AI workloads.
Nice to have
- Experience with AI compilers, tensor or graph compilers, machine learning frameworks, or high-performance computing. - Demonstrated ability to lead complex technical initiatives and deliver measurable improvements in latency, throughput, and hardware utilization. - Experience using AI-assisted development tools or applying AI to compiler and kernel optimization.
Skills: compiler optimizations, LLVM/MLIR, GPU architectures, GPU kernels, CUDA, HIP, parallel programming models
This role has been open 98 days — well above the 57-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · GPU Software Stack
|
Open roles in category
225
|
Median days open
57 d
|
Median salary
$229k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | AMD | All employers we track in this specialty (225 roles · 18 employers) |
|---|---|---|
| Open roles in this specialty | 53 | 225 |
| Open roles in the wider Software, Firmware & Systems family | 410 | 6222 · 145 employers |
| Median days open | 54 d | 57 d (−3 d vs this employer) |
| Median salary (USD postings) | — | $229k |
Skills observed across this category: compiler optimizations, LLVM/MLIR, GPU architectures, GPU kernels, CUDA, HIP, parallel programming models
Who's hiring in this category
- NVIDIA · 111 open roles · median 56 d
- AMD (this employer) · 50 open roles · median 62 d
- Intel Corporation · 24 open roles · median 11 d
- Qualcomm · 18 open roles · median 124 d
- Arm Holdings · 5 open roles · median 117 d
- FuriosaAI · 2 open roles · median 85 d
How we counted: 225 open Infrastructure/Platform Software (GPU Software Stack) roles from 18 employers tracked in the SemiconductorJobs index, counted 20 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.