About the job
Qualcomm AI Hub is the platform for on-device AI — enabling developers to easily integrate, optimize, profile, 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 — Lite RT, ONNX Runtime (ORT), 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 Workbench Cloud Services team and work on the infrastructure that drives on-device AI! Workbench uses real devices in the cloud to enable customers to profile and validate ML models. You will work on the integration of Lite RT, ORT and QAIRT with Qualcomm devices spanning Android, Linux, and Windows, with dispatch to CPU, GPU and NPU. Opportunities abound on this very senior team which operates a one-of-a-kind cloud service.
Responsibilities
Design, develop, and maintain on-device ML profiler applications for Android, Linux, and Windows.
Integrate and support ML runtime frameworks (currently Lite RT, ORT, QAIRT) in the on-device profiler.
Collaborate with partner teams inside Qualcomm, Google, and Microsoft to define requirements and new features.
Work on cutting-edge hardware and ML runtime frameworks.
Bring-up new Qualcomm hardware in AI Hub Workbench.
Support operational issues in device integrations.
Integrate with multiple cloud service device providers.
Collaborate with other AI Hub teams to provide device and ML runtime support.
Qualifications
Minimum
• 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.
Preferred
3+ years of industry experience in ML frameworks or C++ systems engineering.
Proficient in Python.
Experience with ML model concepts (graphs, operators, shapes, backend lowering).
Experience with cross-platform C++ development, CMake, Android, Linux, Windows.
Strong written and verbal communication skills; proficiency with git and software engineering best practices.