Machine Learning Compiler Engineer
Core
Developing and optimizing multi-tier ML compilers for Qualcomm's accelerators (Hexagon, Adreno, low-power ML, CPU) to map ML algorithms to hardware, incorporating generative AI into the workflow and compilers.
Role type
Senior IC machine learning compiler engineer
Builds
ML compilers and intermediate representations for Qualcomm Hexagon Neural Signal Processor, Adreno GPUs, and CPU accelerators
Domain
Hardware/Software interface, Compiler technology, Generative AI
Deliverable
production ML models
Required skills
Compiler development, Computer architecture, Machine learning, Software engineering, Generative AI integration
Preferred skills
MLIR/MLIR dialects, PyTorch 2.0, TVM, Triton, LLVM, DSL design, High-performance computing, Polyhedral optimization, Loop transformation, GPU programming
Technologies
Hexagon-MLIR, LLVM, MLIR, Triton, Torch-MLIR, PyTorch, TVM
Responsibilities
Improve ML compiler optimization via benchmark analysis and profiling, Innovate new ML compiler and optimization algorithms, Incorporate generative AI into compiler development, Upstream compiler algorithms to open-source projects, Author research publications and represent the company in conferences
Seniority
Senior, hands-on IC with substantial responsibility
