The role involves working with the Qualcomm AI Hub Compiler team to develop and maintain the end-to-end compilation pipeline for on-device AI models. The focus is on optimizing and validating ML models for Qualcomm devices, ensuring efficient execution across various hardware backends. The position requires collaboration with multiple teams to enhance model performance and onboarding processes. It also includes authoring technical documentation for the developer community.

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of relevant work experience, or a Master's degree with 3+ years, or a PhD with 2+ years.
• 3+ years of industry experience in ML infrastructure, compiler engineering, or AI framework development.
• Proficient in Python and C++.
• Solid understanding of ML compiler concepts and hands-on experience with compiler stacks such as MLIR, ONNX, or TVM.

• Design, develop, and maintain the compilation pipeline for Qualcomm AI Hub Workbench.
• Build and maintain ONNX-based compilation paths and PyTorch compilation paths.
• Contribute to ONNXRuntime QNN execution provider for graph optimizations and op validation.
• Collaborate with internal teams to ensure correct model execution across CPU, GPU, and NPU.
• Own compilation and validation of models published on Qualcomm AI Hub.
• Build and maintain automated compilation pipelines and CI/CD evaluation harnesses.
• Author technical documentation, tutorials, and example notebooks for the developer community.

• Qualcomm offers competitive compensation, annual bonuses, stock programs, comprehensive healthcare coverage, retirement plans, wellness programs, parental leave, flexible work options, and professional development opportunities.