Senior Staff Software Engineer, AI Edge

Job description

Train task-specific models of in app AI (tiny Gemma/Juno Nano), enabling Gemma model/runtime co-design (quantization, conversion), build industry-leading on-device AI solutions (voice translate, generative image editing). Enable developers to test/evaluate/deploy across devices (Edge Portal /Model Explorer/Developer Device Platform). Develop and guide critical projects in Google's on-device ML infrastructure (e.g., LiteRT, LiteRT-LM). Enable on-device deployment of key models, such as Gemini Nano and Gemma, across various accelerators (GPU /Pixel TPU /NPUs/CPU) on Android, Chrome, and more. Improve performance of on-device model inference via optimizations in the model representation, on-device runtime and kernel implementation. Minimum Qualifications: Bachelor’s degree or equivalent practical experience. 8 years of experience in software development. 7 years of experience leading technical project strategy, ML design, and working with industry-scale ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning). 5 years of experience with design and architecture; and testing/launching software products. Experience with machine learning infrastructure, C++, performance, GPU programming, mobile GPU. Preferred Qualifications: Master’s degree or PhD in Engineering, Computer Science, or a related technical field. Experience with on-device ML Software Development Kits (SDKs)/tooling (e.g., TensorFlow Lite, ExecuTorch, Core ML, SNPE/QNN). In-depth knowledge of ML converters/compilers and runtimes, and hardware-accelerated ML inference techniques. Strong understanding of generative AI model architectures and their optimization for on-device execution. Proven track record of leading and delivering successful ML projects focused on on-device deployment (Android, iOS, web browsers, or embedded devices).