13 hours ago
Base Salary
$174k - $252k/yr
Responsibilities
- Write and test product or system development code.
- Triage, debug, track, and resolve product or system issues by analyzing effects on hardware, network, service operations, and quality.
- Develop LiteRT for first-party and third-party on-device AI use cases and hardware acceleration.
- Enable deployment of models such as Gemini Nano and Gemma across GPUs, Pixel TPUs, NPUs, and CPUs on Android, Chrome, and other platforms.
- Improve on-device inference performance through model conversion, runtime, and kernel implementation optimizations.
Requirements
- Bachelor’s degree or equivalent practical experience.
- At least 5 years of software development experience in one or more programming languages.
- At least 3 years of experience testing, maintaining, or launching software products and 1 year of software design and architecture experience.
- At least 3 years of experience in speech/audio, reinforcement learning, ML infrastructure, or another ML specialization.
- At least 3 years of end-to-end machine learning experience, including model deployment, model evaluation, data processing, and debugging.
- Preferred: master’s degree or PhD in computer science or a related technical field.
- Preferred: 5 years of experience with data structures and algorithms.
- Experience with on-device ML SDKs and tooling such as TensorFlow Lite, ExecuTorch, Core ML, or SNPE/QNN.
- Knowledge of ML converters, compilers, hardware-accelerated ML inference techniques, and ML frameworks such as PyTorch, JAX, or TensorFlow.
- Understanding of generative AI model architectures and their optimization for on-device execution.
Benefits
- US base pay is $174000-$252000, plus a 15% bonus target, equity, and benefits.
- Google provides additional benefits information through its benefits program.
Tech Stack
PyTorchTensorFlow
Categories
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.