Staff Software Engineer, Scaling On-Device ML Frameworks

Google Cloud is seeking a Staff Software Engineer to work on scaling on-device ML frameworks. The role involves developing next-generation technologies that change how billions of users connect, explore, and interact with information. The focus is on On-Device Machine Learning (ML), especially with the rise of Generative AI, which is central to Google's product portfolio. The team is building core capabilities powering unique experiences on Pixel and Android, such as Speech Recognition, Camera, and Assistant/Translation.

Key responsibilities include:

1. Integrating frameworks like Hugging Face/JAX/PyTorch with AI Edge Torch and MP LLM Inference API.
2. Developing sample apps demonstrating best practices in hardware acceleration, quantization, debugging, and optimizing performance and quality.
3. Onboarding state-of-the-art models to provide excellent self-serve out-of-the-box experiences for users.
4. Scaling partnerships with Android Apps and Google Cloud Customers and driving improvements in the overall stack based on real customer needs.
5. Implementing automated processes and infrastructure to test APIs and user-journeys across diverse platforms.

The ideal candidate should have experience with frameworks such as JAX and PyTorch, full-stack Android, iOS, and Web development, OSS development, on-device machine learning deployment, Machine Learning infrastructure, Mobile App Development, and Integration Testing. Experience with iOS Development, Android Development, C++, and Python is preferred.

Google Cloud offers enterprise-grade solutions leveraging cutting-edge technology and tools for developers to build more sustainably. The company is committed to diversity, equality, and inclusion, providing equal employment opportunities to all candidates.