Senior Software Engineer, ChromeOS, On-Device Machine Learning at Google

Taipei, , Taiwan -

Full Time

Start Date

Immediate

Expiry Date

04 Feb, 26

Salary

0.0

Posted On

06 Nov, 25

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Software Development, Machine Learning, Performance Analysis, Optimization, Python, C, C++, ML Frameworks, On-Device Deployment, TensorFlow Lite, Generative AI, Model Compilation, Benchmarking, Debugging, Data Processing, Fine Tuning

Industry

Software Development

Description

MINIMUM QUALIFICATIONS: * Bachelor's degree or equivalent practical experience. * 5 years of experience with software development in one or more programming languages (e.g., Python, C, C++). * 5 years of experience testing, and launching software products. * 3 years of experience leading technical project strategy, ML design, and working with industry-scale ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning). * 3 years of experience in performance analysis and optimization including GPU programming, mobile GPU, system architecture, performance modeling, benchmarking, machine learning infrastructure, or other similar experience. PREFERRED QUALIFICATIONS: * Experience with ML frameworks (e.g., PyTorch, JAX, TensorFlow). * Experience leading and delivering ML projects focused on on-device deployment (Android, iOS, web browsers, or embedded devices). * Experience with on-device ML SDKs/tooling (e.g., TensorFlow Lite). * Knowledge of ML converters/compilers and run-times, and hardware-accelerated ML inference techniques. * Understanding of Generative AI model architectures and their optimization for on-device execution. * Passion for innovation and for driving progress in 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. Our team focuses on model quality, outputs, compilation to achieve a wide range of capabilities on device, and work with other teams in the Laptops & Tablets On-Device Machine Learning (L&T ODML) to build APIs for building engaging user experiences on device. In this role you will be responsible for learning the foundations of ML modeling, neural networks, transformers, Generative Artificial Intelligence (genAI), optimization techniques like quantization, model compilation and op fusing, fine-tuning techniques like prompt tuning, and how they tie into the inference software stack to run across the entire laptop and tablet fleet of Android devices. ChromeOS delivers quality computing at scale to provide universal and unfettered access to information, entertainment, and tools. Our mission is to empower anyone to create and access information freely through fast, secure, simple, and intelligent computing. RESPONSIBILITIES: * Bringup ML and GenAI models onto various compute (CPU, GPU and NPUs) across suite of devices (laptops and tablets). * Test and benchmark model performance and quality across varying sizes and constraints. * Work on fine-tune training and model quality optimizations along with model compilation and training. * Build inference graphs that can leverage on-device models. * Collaborate with power and performance teams to optimize model power/compute usage and memory footprint.

Responsibilities

You will be responsible for bringing up ML and GenAI models onto various compute platforms and testing their performance and quality. Collaboration with power and performance teams will be essential to optimize model power and compute usage.