Qualcomm Technologies’ Compiler Labs unit in the AI Software department is seeking Machine Learning Compiler Engineers at multiple levels, from entry-level to experienced. The team improves existing machine-learning compilers and develops new compiler technologies for mapping ML algorithms to accelerators, including Qualcomm Hexagon Neural Signal Processors, Adreno GPUs, low-power ML accelerators, and CPU accelerators. The work applies advanced mathematics, algorithms, programming-language concepts, and compiler technologies to optimization challenges in modern machine learning. Areas include multi-tier compiler design and phase ordering, polyhedral optimization, dataflow concepts, structured speculation, communication-avoiding algorithms, intermediate representations, and correctness verification for programs using quantized neural operators. The team also contributes to open-source LLVM and MLIR ecosystem work, including Hexagon-MLIR, Triton, and Torch-MLIR flows. Generative AI is part of both the compiler-development workflow and the capabilities built into compilers. Engineers are expected to incorporate generative AI into their work. The team emphasizes precise program representations, advanced optimization methods, strong software engineering, and delivering compilers with meaningful impact on Qualcomm’s business. Positions are available in New York City, Austin, San Diego, and Raleigh, North Carolina. Remote arrangements may be considered for experienced candidates. Senior-level engineers lead and manage projects while continuing substantial technical work.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Entry Level