7 days ago
Base Salary
$131k - $181k/yr
Responsibilities
- Design and implement core ML runtime framework components for embedded inference.
- Collaborate with compiler, hardware, and model teams on efficient AI workload execution paths.
- Develop and maintain C++ runtime kernels and system-level integrations.
- Create tools for performance profiling and debugging quantized model accuracy.
- Analyze runtime behavior using profiling tools and hardware counters, and improve performance.
- Support deployment of models from ONNX, TensorFlow, and PyTorch onto Qualcomm’s inference stack.
Requirements
- Bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field plus 4+ years of relevant engineering experience; alternatively, a master’s degree plus 3+ years or a PhD plus 2+ years.
- Strong hands-on experience optimizing performance for embedded or low-power systems.
- Excellent C++ programming skills focused on system-level and runtime development.
- Solid understanding of embedded system design, memory hierarchy, and hardware-software interaction.
- Experience with Linux, Android, or QNX development environments and toolchains.
- Familiarity with computer architecture, AI accelerators, or DSPs.
- Solid knowledge of machine learning concepts, model structures, deep learning, and popular ML frameworks.
- Experience optimizing algebraic operations in algorithms for hardware cores.
Benefits
- Competitive annual discretionary bonus program and opportunity for 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.