Join Qualcomm's Low Power AI solution team as a Machine Learning Engineer, focusing on deploying innovative AI models with low power consumption. Your expertise will be vital in enhancing inference efficiency on cutting-edge hardware.
This role involves deep collaboration with teams to design and optimize models for Qualcomm's AI accelerators. You'll explore emerging ML architectures, improve quantization techniques, and evaluate performance trade-offs. Your hands-on experience will drive model-hardware co-design and contribute significantly to low-power inference technologies.
Key Responsibilities: • Prototype novel ML model architectures for low-power inference • Align model design with Qualcomm’s AI accelerator capabilities • Optimize quantization and mixed-precision techniques • Develop and refine computational graphs and scheduling strategies • Conduct performance evaluations using profiling tools