Senior Staff Compiler Engineer - MLIR/LLVM for GPUs

AMD; San Jose (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

AMD's San Jose-based team seeks a Senior Staff Software Engineer to lead compiler development for AI/compute platforms and optimize GPU performance. You will design MLIR/LLVM-based compiler tech, develop code-generation flows, and work with GPU architecture, runtime, and AI framework teams to deliver top-tier performance.

The ideal candidate is a technical leader with deep compiler, GPU, and performance expertise, capable of spanning from high-level graph transformations to low-level code

Qualifications

• Deep hands-on experience with MLIR, LLVM, compiler optimization, lowering, and code generation.
• Strong knowledge of compiler architecture, IRs, 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.
• Experience with AI compilers, tensor or graph compilers, ML frameworks, or HPC.
• Demonstrated ability to lead complex technical initiatives and deliver improvements in latency, throughput, and hardware utilization.
• Experience using AI-assisted development tools or applying AI to compiler and kernel optimization.

Responsibilities

• Design and implement compiler optimizations using MLIR and LLVM for GPU and AI workloads.
• Develop compiler passes, IRs, 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 and memory bandwidth.
• 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 co-design.
• Build profiling, benchmarking, autotuning, and performance regression infrastructure.
• Apply AI and coding agents to compiler development, kernel optimization, debugging, test generation, and performance analysis.
• Provide technical leadership, drive architecture decisions, and mentor engineers across compiler and GPU projects.

Skills

MLIR

LLVM

GPU architecture

C/C++

Education

Bachelor's degree in Computer Science or related field

Master's degree or Doctorate preferred

Tools

HIP

CUDA

Job description

AMD's San Jose-based team seeks a Senior Staff Software Engineer to lead compiler development for AI/compute platforms and optimize GPU performance. You will design MLIR/LLVM-based compiler tech, develop code-generation flows, and work with GPU architecture, runtime, and AI framework teams to deliver top-tier performance.

The ideal candidate is a technical leader with deep compiler, GPU, and performance expertise, capable of spanning from high-level graph transformations to low-level code