Drive AI innovation with Qualcomm Canada as a Machine Learning Engineer. Contribute to advanced model efficiency and ML system optimization for on-device inference solutions.As part of the Low Power AI Solution team, you will engage in cutting-edge research focusing on inference efficiency and system optimization. Collaboration with global teams will be key as you design efficient architectures and streamline model compression techniques. This role emphasizes hands-on development and strategic initiatives, shaping the future capabilities of Qualcomm’s AI accelerators.Key Responsibilities:
- Conduct research on model compression and inference efficiency
- Develop software-hardware co-design system solutions
- Collaborate with teams to create low power AI systems
- Influence future accelerator features and deployment strategies
- Convert research findings into production-ready solutionsRequirements:
- Proven research records in inference efficiency
- Expertise in model compression and neural network architectures
- Background in compiler stack optimization for AI accelerators
- Robust programming skills with ML frameworks
- Experience with AI accelerator model development pipelinesLeverage your expertise to redefine AI capabilities at Qualcomm Canada.#J-18808-Ljbffr