NPU Compiler Engineer

What you'll do

• Design and implement compiler passes in the MLIR framework to optimize AI workloads on NPUs.
• Analyze and debug functional and performance issues within the compiler tool stack.
• Build infrastructure for the analysis and debugging of regression suites.
• Integrate AI and coding agents into compiler development, debugging, test generation, and performance analysis.
• Apply a data-driven approach to target optimization efforts for machine learning networks.
• Research and implement more efficient methods to resolve existing technical issues.
• Develop and maintain technical relationships with internal peers and external partners.

What we're looking for

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
• Strong object-oriented programming background (C/C++ preferred).
• Deep hands-on experience with MLIR optimization and lowering passes (preferred).
• Strong knowledge of compiler architecture, intermediate representations, transformation passes, and optimization pipelines (preferred).
• Strong understanding of NPU architecture, including parallel execution, memory hierarchy, caches, registers, synchronization, and occupancy (preferred).
• Strong C++ and Python skills (preferred).
• Experience with AI compilers, tensor or graph compilers, and machine learning frameworks (preferred).
• Experience with debugging using SystemC and RTL simulators (preferred).