This role pays more than
74%
of similar roles. Most pay
$185,243–$254,750
— the shaded band above.
At the midpoint, this role pays about
$251k
versus about
$220k
for comparable roles.
Based on 240 similar postings.
Employer
About Qualcomm
Qualcomm is a leading American semiconductor and telecommunications company based in San Diego, CA.
Qualcomm currently has
623 open roles
on FindRole.
Listed pay typically runs
$148,300–$222,500
across 603 roles with salary data.
The Machine Learning Compiler Engineer joins the Compiler Labs unit within the AI Software department to develop and improve innovative machine learning compilers. This role involves mapping complex machine learning algorithms to various hardware accelerators, including the Hexagon Neural Signal Processor, Adreno GPUs, and low-power units. Day-to-day responsibilities include optimizing compiler capabilities through benchmark analysis, innovating new optimization algorithms, incorporating generative AI into development workflows, and upstreaming algorithms to open-source projects like LLVM and MLIR. The work focuses on solving challenges in polyhedral optimization for generative AI, communication-avoiding algorithms from high-performance computing, and correctness verification for quantized neural operators. Required skills include expertise in compiler development, computer architecture, and machine learning. Preferred technical proficiencies include MLIR dialects, PyTorch 2.0, TVM, Triton, LLVM, loop transformation, vectorization, and GPU programming.