27 days ago
Base Salary
$161k - $241k/yr
Responsibilities
- Design, develop, and maintain the full Qualcomm AI Hub compilation pipeline from PyTorch and ONNX ingestion through graph optimization and deployment to LiteRT, ONNXRuntime, or QAIRT.
- Develop ONNX IR graph transformation, operator validation, opset compatibility, PyTorch torch.export, dynamic-shape, custom-op, and ATen IR decomposition workflows.
- Contribute graph optimizations, partitioning, operator validation, and lowerings to the ONNXRuntime QNN execution provider.
- Collaborate with QAIRT and QNN teams to optimize model execution across CPU, GPU, and NPU backends.
- Build profiling, debugging, diagnostics, automated compilation, and validation tooling for model correctness and performance at scale.
- Own compilation and validation of models published on Qualcomm AI Hub and partner with business units to onboard models under deployment constraints.
- Write technical documentation, tutorials, and example notebooks for the Qualcomm AI Hub developer community.
- Provide technical guidance and mentorship while influencing the compiler roadmap, model catalog strategy, and runtime integration priorities.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field plus 4+ years of relevant experience; or a master’s degree plus 3+ years; or a PhD plus 2+ years.
- 3+ years of industry experience in ML infrastructure, compiler engineering, or AI framework development is preferred.
- Proficiency in Python and C++ and understanding of ML compiler concepts including graph IRs, operator fusion, shape inference, lowering passes, and backend partitioning.
- Hands-on experience with compiler stacks such as MLIR, ONNX, or TVM is preferred.
- Experience with PyTorch model export technologies including torch.export, torch.compile, FX, or ATen IR and deployment frameworks such as LiteRT, ExecuTorch, or ONNXRuntime.
- Familiarity with SoC constraints, NPU/DSP execution, QAIRT/QNN, and automated CI/CD pipelines for model compilation and validation is preferred.
- Strong written and verbal communication skills, Git proficiency, and software engineering best practices.
Benefits
- Competitive annual discretionary bonus program and potential annual RSU grants.
- Competitive benefits package supporting employees at work, at home, and at play.
Categories
About Qualcomm
Inspired by 250 years of American ingenuity, we build technologies that expand what’s possible. From wireless to AI at scale and 6G, our innovations power progress worldwide.