9 hours ago
London, United KingdomStaff+
Responsibilities
- Architect, design, and build distributed asynchronous AI systems spanning smart glasses, mobile devices, and cloud infrastructure.
- Lead production integration of computer vision, language, and multimodal models, including routing, confidence calibration, abstention, and verification mechanisms.
- Drive performance and reliability trade-offs across latency, bandwidth, compute, memory, battery life, thermal limits, and inference cost.
- Co-design constrained edge and mobile inference pipelines with machine learning researchers and hardware teams using quantization, model compression, and hardware acceleration.
- Establish evaluation frameworks, observability, and debugging tools to improve end-to-end system performance and user experience.
Requirements
- Bachelor's degree or equivalent practical experience.
- At least 8 years of experience with C++ or Python, modern ML frameworks such as JAX or PyTorch, and on-device or cloud inference runtimes.
- Experience optimizing latency, bandwidth, reliability, compute, memory, energy, and cost across device, mobile, and cloud layers.
- Experience with asynchronous architectures, streaming data, state management, buffering, backpressure, fault tolerance, observability, and production debugging.
- Preferred: PhD in Distributed Systems for advanced Machine Learning or Embedded Systems.
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.