Developing and training edge optimized models for generative AI, computer vision, natural language and speech use cases at Google
Requirements
2 years of experience with software development in one or more programming languages (C++, Python), or 1 year of experience with an advanced degree
2 years of experience working with machine learning/artificial intelligence
Master's degree or PhD in Computer Science or related technical field with an emphasis on Machine Learning/Artificial Intelligence
Experience in developing, training, and optimizing machine learning models
Experience working with any deep learning frameworks – Tensorflow, Pytorch or JAX
Experience with accelerators or working at the hardware/software interface
Experience with neural network architectures/design
Responsibilities
Lead efforts on defining, developing and training edge optimized models for generative AI, computer vision, natural language and speech use cases
Design, build, and maintain model optimization tools and infrastructure modules needed for automating optimization and training of neural networks and architecture design space exploration
Write modular and efficient ML training pipelines and assist in building profiling and visualization tools
Work with EdgeTPU architects to design future accelerators, the hardware/software interface, and co-optimizations of the next generation EdgeTPU architectures
Collaborate with ML model developers, researchers, and EdgeTPU hardware/software teams on customize neural network architectures to accelerate the transition from research ideas to user experiences running on the EdgeTPU
Other
Bachelor’s degree or equivalent practical experience
Adaptable individual with a naturally enthusiastic and optimistic outlook
Preferred working location from the following: Mountain View, CA, USA; Kirkland, WA, USA
