On-Device ML Engineer for LiteRT & Edge AI

Google Inc.; Sunnyvale (CA); On-site; USD 147,000 - 210,000; Full time

Job summary

Google Inc. in Sunnyvale, CA, is seeking a Software Engineer focused on On-Device Machine Learning to advance LiteRT and edge AI across Google products.

The role emphasizes implementing and optimizing ML models for mobile and embedded platforms, with opportunities to collaborate across teams and mentor junior engineers. The candidate will deploy and optimize models on-device, work with accelerators like GPU/TPU/NPUs, and contribute to infrastructure supporting on-device AI at scale.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with software development in one or more programming languages, or 1 year of experience with an advanced degree.
• 2 years of experience with ML infrastructure (e.g., model deployment, model evaluation, optimization, data processing, debugging).
• Experience with runtimes and performance tuning.

Responsibilities

• Collaborate with peers through design and code reviews to ensure best practices.
• Implement solutions in ML areas, utilize ML infrastructure, and contribute to model optimization and data processing.
• Develop LiteRT, Google’s on-device AI framework for first- and third-party use cases.
• Enable on-device deployment of models across accelerators (GPU/Pixel TPU/NPUs/CPU).
• Improve performance of on-device model inference via runtime and kernel optimizations.

Skills

Problem solving

Mentoring

Software development

Education

Bachelor’s degree

Master’s degree preferred

Tools

PyTorch

TensorFlow

JAX

Core ML

Job description

Google Inc. in Sunnyvale, CA, is seeking a Software Engineer focused on On-Device Machine Learning to advance LiteRT and edge AI across Google products.

The role emphasizes implementing and optimizing ML models for mobile and embedded platforms, with opportunities to collaborate across teams and mentor junior engineers. The candidate will deploy and optimize models on-device, work with accelerators like GPU/TPU/NPUs, and contribute to infrastructure supporting on-device AI at scale.