Staff Machine Learning Engineer – AI/ML Compiler

Company: Qualcomm Technologies, Inc. Job Area: Engineering Group, Engineering Group > Machine Learning Engineering General Summary:

Qualcomm AI Hub is the platform for on-device AI — enabling developers to easily integrate,   optimize , and deploy ML models on Qualcomm devices. Qualcomm AI Hub Workbench lets developers compile trained   PyTorch   or ONNX models into deployable artifacts targeting a variety of runtimes —   LiteRT ,   ONNXRuntime , or Qualcomm AI Engine Direct SDK (QAIRT) — and profile and   validate   them on real Qualcomm devices hosted in the cloud.   Join the Qualcomm AI Hub Compiler team and own the infrastructure that powers these model compilations. You will work across the full compilation pipeline — from model ingestion and graph optimization to backend dispatch across CPU, GPU, and NPU — ensuring models compile correctly, execute efficiently, and scale across a growing catalog of on-device use cases spanning vision, audio, speech, and multi-modal models.

Compiler Pipeline & Infrastructure   Design, develop, and   maintain   the end-to-end compilation pipeline powering Qualcomm AI Hub Workbench, from   PyTorch   and ONNX model ingestion through graph optimization to deployable artifacts targeting   LiteRT ,   ONNXRuntime , or QAIRT on Snapdragon SoCs   Build and maintain ONNX-based compilation paths using ONNX IR: graph transformation passes, op validation, and   opset   compatibility handling   Build and maintain   PyTorch   compilation paths consuming   torch.export   output, including dynamic shapes, custom ops, and   ATen   IR decomposition   Contribute to   ONNXRuntime   QNN execution provider: graph optimizations, graph partitioning, and op validation and   lowerings   Collaborate with QAIRT and QNN teams to ensure correct and efficient model execution across CPU, GPU, and NPU backends   Build tooling to analyze, profile, and debug compilation failures, accuracy regressions, and performance degradations; develop clear, actionable developer-facing diagnostics   Model Catalog, Automation & Collaboration   Own compilation and validation of models published on Qualcomm AI Hub, ensuring correct conversion and verified performance across supported runtime targets   Build and   maintain   automated compilation pipelines and CI/CD evaluation harnesses to scale model onboarding as the Qualcomm AI Hub model catalog grows   Partner with internal Business Units to onboard models through Qualcomm AI Hub compilation workflows, translating deployment constraints (target SoC, latency budgets, memory limits) into concrete compilation strategies   Author technical documentation, tutorials, and example notebooks for the Qualcomm AI Hub developer community   Minimum Qualifications: • Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience. OR Master's degree in Computer Science, Engineering, Information Systems, or related field and 3+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience. OR PhD in Computer Science, Engineering, Information Systems, or related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.

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 (graph IRs, operator fusion, shape inference, lowering passes, backend partitioning) and hands-on experience with one or more compiler stacks such as MLIR, ONNX, or TVM   Experience with   PyTorch   model export ( torch.export ,   torch.compile , FX,   ATen   IR) and on-device deployment frameworks such as   LiteRT ,   ExecuTorch , or