Qualcomm is committed to enabling the wide deployment of intelligent solutions on all possible devices and is creating the building blocks for the intelligent edge. This role focuses on advancing Gen AI Technology for the Edge, including model fine tuning, hardware acceleration, model quantization, and edge inference.
Requirements
- Strong Software Engineering/Development skills combined with a solid foundation in AI and general ML techniques.
- Proven hands-on experience evaluating and optimizing Generative AI workflows for accuracy, performance, and other key metrics.
- Prior experience with ML model optimization frameworks and a familiarity with applying techniques such as quantization, pruning etc.
- Knowledge of neural networks, with hands-on experience using ML frameworks such as PyTorch, ONNX etc.
- Strong Python design and implementation skills.
- Strong general analytical and debugging skills.
- Experience deploying GenAI LLM/LVM models on edge devices.
Responsibilities
- Architect, design, develop and test model optimization techniques that include - but are not limited to - graph optimization, pruning and quantization.
Other
- Work in a dynamic research environment,
- Be part of a multi-disciplinary team of researchers and software engineers who work with cutting edge AI frameworks and tools.
- Prior experience working in agile environments.
- Prior experience in collaborating with multi-disciplinary teams across time zones.
- Strong leadership skills as a mentor, team player, communicator and presenter.
