9 hours ago
Munich, GermanySenior
Responsibilities
- Produce multi-task generative models directly on-device for real-time, low-latency image editing.
- Develop reusable cross-platform C++ APIs and native Android and iOS wrappers for partner applications.
- Integrate and deploy multimodal on-device models such as Gemma across text, audio, image, and video.
- Optimize and port goal-segmentation models to edge devices and mobile GPU/TPU pipelines.
- Build low-latency audio and speech pipelines using optimized C++ code and MediaPipe graphs.
Requirements
- Bachelor’s degree or equivalent practical experience.
- At least 2 years of software development experience in one or more programming languages, or 1 year with an advanced degree.
- At least 1 year of experience with ML infrastructure such as model deployment, model evaluation, data processing, or debugging.
- Experience with on-device ML SDKs or tooling such as MediaPipe, TensorFlow Lite, ExecuTorch, Core ML, SNPE, or QNN.
- Preferred: master’s degree or PhD in Computer Science or a related technical field.
- Preferred: proven experience leading and delivering on-device AI/ML projects for Android, iOS, web browsers, or embedded devices.
- Strong communication, collaboration, and innovation skills.
Tech Stack
C++iOS
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.