Software Engineer, On-Device Machine Learning

About the role

MINIMUM 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.
• Experience in mobile development.

PREFERRED QUALIFICATIONS:

• Master's degree or PhD in Computer Science or related technical fields.

• Experience in leading and delivering successful ML projects focused on

on-device deployment (Android, iOS, web browsers, or embedded devices).

• Experience in ML frameworks (e.g., PyTorch, JAX, TensorFlow).
• Experience with on-device ML SDKs/tooling (e.g., TensorFlow Lite, ExecuTorch,

Core ML, SNPE/QNN).

• Strong understanding of Generative AI model architectures and their

optimization for on-device execution.

• Passion for innovation and a strong desire to push the boundaries of what's

possible with on-device ML.

ABOUT THE JOB:

Google's software engineers develop the next-generation technologies that change

how billions of users connect, explore, and interact with information and one

another. Our products need to handle information at massive scale, and extend

well beyond web search. We're looking for engineers who bring fresh ideas from

all areas, including information retrieval, distributed computing, large-scale

system design, networking and data storage, security, artificial intelligence,

natural language processing, UI design and mobile; the list goes on and is

growing every day. As a software engineer, you will work on a specific project

critical to Google’s needs with opportunities to switch teams and projects as

you and our fast-paced business grow and evolve. We need our engineers to be

versatile, display leadership qualities and be enthusiastic to take on new

problems across the full-stack as we continue to push technology forward.

LiteRT is Google’s on-device AI framework, succeeding TensorFlow Lite (TFLite).

It improves the performance, efficiency, and portability of ML models across

edge devices from mobile phones to embedded systems. LiteRT significantly

upgrades GPU acceleration and introduces native NPU acceleration, while

maintaining and enhancing the robust CPU performance inherited from TFLite.

LiteRT enables developers and Google products to deploy AI across mobile, web,

desktop, and embedded. Our team focuses on building cross-platform

infrastructure aligned with Google's business needs, serving Google products

(Android, Chrome, Photos, Meet, YouTube, etc.), third-party developers, and

specialized Pixel solutions. Our goal is to provide on-device AI infrastructure

with exceptional performance, enabling framework and device flexibility at

scale.

Google Cloud accelerates every organization’s ability to digitally transform its

business and industry. We deliver enterprise-grade solutions that leverage

Google’s cutting-edge technology, and tools that help developers build more

sustainably. Customers in more than 200 countries and territories turn to Google

Cloud as their trusted partner to enable growth and solve their most critical

business problems.

Individual pay is determined by factors including job-related skills,

experience, and relevant education or training.

US: $147000 - $210000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google

[https://www.google.com/about/careers/applications/benefits/].

RESPONSIBILITIES:

• Collaborate with peers and stakeholders through design and code reviews to

ensure best practices amongst available technologies (e.g., style guidelines,

checking code in, accuracy, testability, and efficiency).

• Implement solutions in one or more specialized 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,

enabling SOTA hardware acceleration and use cases on edge platforms.

• Enable on-device deployment of key models, such as Gemini Nano and Gemma,

across various accelerators (GPU/Pixel TPU/NPUs/CPU) on Android, Chrome, iOS,

desktop, and more.

• Improve performance of on-device model inference via optimizations in

on-device runtime and kernel implementation.