Staff Software Engineer, On-Device Machine Learning

Google•Sunnyvale, CA

3d•$207,000 - $300,000

About The Position

Google is seeking a software engineer to work on Google AI Edge, which enables Google products and developers to deploy AI across mobile, web, and embedded platforms. The team builds cross-platform infrastructure and solutions for Google AI, including tools, models, and infrastructure serving Google apps, platforms, devices, and third-party developers. The role focuses on enabling on-device machine learning and AI Edge developer tools, training task-specific models, supporting model and runtime co-design, and deploying models across devices and hardware accelerators. The engineer will improve on-device inference performance through optimizations to model presentation, runtime, and kernels, and will contribute to products and infrastructure used across Android, iOS, web, Chrome, and devices.

Requirements

Bachelor’s degree or equivalent practical experience.
8 years of experience in software development.
5 years of experience with software development in C++.
5 years of experience testing and launching software products.
3 years of experience with software design and architecture.
5 years of experience leading ML design and optimizing end-to-end machine learning, such as model deployment, model evaluation, data processing, debugging, and fine-tuning.

Nice To Haves

Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
8 years of experience with data structures and algorithms.
3 years of experience in a technical leadership role leading project teams and setting technical direction.
3 years of experience working in a complex, matrixed organization involving cross-functional or cross-business projects.
Experience deploying on-device machine learning models.

Responsibilities

Enable areas of Google AI Edge Developer Tools, such as AI Edge Gallery, Developer Device Platform, and AI Edge Eval.
Train task-specific models for in-app AI and enable Gemma model/runtime co-design, including quantization and conversion.
Build on-device AI solutions, including voice translation and generative image editing.
Enable tooling for go-to-market support of on-device Gemma launches, helping developers test, evaluate, and deploy across devices.
Enable deployment of key models across GPU, Pixel TPU, NPUs, and CPU on Android, Chrome, and other platforms.
Improve on-device model inference performance through optimizations to model presentation, on-device runtime, and kernel implementation.