Edge AI Engineer: On-Device ML & Optimization

Socket.dev; San Diego (CA); On-site; USD 123,000 - 184,000; Full time

Job summary

Qualcomm AI Research is seeking AI software engineers to enable GenAI on edge devices. You will work on end-to-end embedded AI software, optimize ML/AI stacks, and collaborate with hardware teams to deploy models on Qualcomm accelerators for edge devices like smartphones and robotics.

The role emphasizes development, optimization, and debugging tools, with a strong focus on performance and power efficiency. A Bachelor's degree is required, and knowledge of PyTorch and QNN SDK is a plus.

Qualifications

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field.

Responsibilities

• Development of end-to-end embedded AI software to train and finetune neural network models on Qualcomm leading edge hardware with optimal resources.
• Design and enhance the implementation of ML/AI SW stack, kernels, and runtime software to improve performance and power efficiency.
• Collaborating with our AI Processor Hardware team to implement high-quality solutions for new ML operators/layers that optimally utilize new capabilities in next-gen AI processors.
• Development of debugging/profiling tools and user-friendly SDKs for customers to foster rapid deployment of their new use cases.

Skills

C/C++

Python

Software design

Android programming

Neural network training

Neural network quantization

QNN SDK

Optimization for HW cores

Education

Bachelor's degree in Computer Science or related field

Tools

PyTorch

Job description

Qualcomm AI Research is seeking AI software engineers to enable GenAI on edge devices. You will work on end-to-end embedded AI software, optimize ML/AI stacks, and collaborate with hardware teams to deploy models on Qualcomm accelerators for edge devices like smartphones and robotics.

The role emphasizes development, optimization, and debugging tools, with a strong focus on performance and power efficiency. A Bachelor's degree is required, and knowledge of PyTorch and QNN SDK is a plus.