Senior Software Engineer, On-Device Machine Learning

Google•Sunnyvale, CA

10d•$174,000 - $252,000

About The Position

Google is seeking a Senior Software Engineer to work on LiteRT, its next-generation on-device AI framework succeeding TensorFlow Lite. LiteRT is designed to maximize the performance, efficiency, and portability of machine-learning models across edge devices, from mobile phones to embedded systems. The role focuses on developing the framework for first- and third-party use, enabling hardware acceleration and on-device use cases across edge platforms, and supporting deployment of models such as Gemini Nano and Gemma across accelerators and platforms. Google software engineers develop technologies used by billions of people and work on projects critical to Google's needs. Engineers are expected to be versatile, demonstrate leadership qualities, and take on new problems across the full stack as the business evolves. Individual pay is determined by factors including job-related skills, experience, and relevant education or training. The stated U.S. compensation is $174,000–$252,000 USD, plus a 15% bonus target, equity, and benefits.

Requirements

Bachelor’s degree or equivalent practical experience.
5 years of experience with software development in one or more programming languages.
3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
3 years of experience in one or more of speech/audio, reinforcement learning, ML infrastructure, or another ML specialization.
3 years of experience with end-to-end machine learning, such as model deployment, model evaluation, data processing, and debugging.

Nice To Haves

Master’s degree or PhD in Computer Science or a related technical field.
5 years of experience with data structures and algorithms.
Experience with on-device ML SDKs or tooling, such as TensorFlow Lite, ExecuTorch, Core ML, or SNPE/QNN.
Knowledge of ML converters and compilers, hardware-accelerated ML inference techniques, and proficiency in ML frameworks such as PyTorch, JAX, or TensorFlow.
Understanding of generative AI model architectures and their optimization for on-device execution.

Responsibilities

Write and test product or system development code.
Triage product or system issues and debug, track, and resolve them by analyzing their sources and impact on hardware, network, or service operations and quality.
Develop LiteRT, Google's on-device AI framework for first- and third-party use, enabling state-of-the-art hardware acceleration and use cases on edge platforms.
Enable on-device deployment of key models, such as Gemini Nano and Gemma, across GPU, Pixel TPU, NPUs, and CPU on Android, Chrome, and other platforms.
Improve on-device model inference performance through optimizations in model conversion, the on-device runtime, and kernel implementation.