Senior Software Engineer, On-Device Machine Learning
$174k - $252k • Sunnyvale, CA, USA • Full-time
Posted 22d ago
Job Location
Sunnyvale, CA, USA
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
Machine Learning Engineer
About the job
Google is seeking experienced software engineers to develop next-generation technologies that impact billions of users globally. This role focuses on LiteRT, Google's advanced on-device AI framework designed to enhance the performance, efficiency, and portability of Machine Learning models across a wide range of edge devices. You will contribute to critical projects, with opportunities to work on diverse challenges and technologies within a fast-paced environment. The ideal candidate is versatile, demonstrates leadership, and is eager to tackle new problems across the full stack.
Responsibilities
- Write and test product or system development code.
- Triage product or system issues, debug, track, and resolve them by analyzing sources and impact.
- Develop LiteRT, Google's on-device AI framework for internal and third-party use, enabling state-of-the-art hardware acceleration on edge platforms.
- Enable on-device deployment of key models like Gemini Nano and Gemma across various accelerators on Android, Chrome, and other platforms.
- Improve on-device model inference performance through optimizations in model conversion, runtime, and kernel implementation.
Requirements
- Bachelor's degree or equivalent practical experience.
- 5 years of software development experience in one or more programming languages.
- 3 years of experience testing, maintaining, or launching software products.
- 1 year of experience with software design and architecture.
- 3 years of experience with Speech/audio, reinforcement learning, ML infrastructure, or another ML specialization.
- 3 years of experience with end-to-end Machine Learning, including model deployment, evaluation, data processing, and debugging.
- Experience with on-device ML SDKs/tooling (e.g., TensorFlow Lite, ExecuTorch, Core ML, SNPE/QNN).
- Knowledge of ML converters/compilers and hardware-accelerated ML inference techniques.
- Proficiency in ML frameworks (e.g., PyTorch, JAX, TensorFlow).
- Understanding of Generative AI model architectures and their optimization for on-device execution.
Benefits
- 15% bonus target
- Equity
- Benefits package
