- NVIDIA (Santa Clara, CA)
- …how you can make a lasting impact on the world. We are seeking a highly-skilled Senior On- Device Model Inference Optimization Engineer to join our team ... you'll be doing: + Develop and implement strategies to optimize AI model inference for on- device deployment. + Employ techniques like pruning, quantization,… more
- Google (Sunnyvale, CA)
- …accelerators (GPU/Pixel TPU/NPUs/CPU) on Android, Chrome, and more. + Improve performance of on- device model inference via optimizations in the model ... Senior Staff Software Engineer, On- Device Machine... inference techniques. + Understanding of generative AI model architectures and their optimization for on- device … more
- LinkedIn (Mountain View, CA)
- …Why join us: If you're passionate about **AI infra, scalable evaluation systems, or model alignment** , and want to see your work directly **safeguard products used ... together. The team is responsible for scaling LinkedIn's AI model training, feature engineering and serving with hundreds of...infra on top of native cloud, enable GPU based inference for a large variety of use cases, cuda… more
- Microsoft Corporation (Mountain View, CA)
- …across Surface devices, Windows Copilot, and the broader Microsoft ecosystem. As a ** Senior AI Engineer** , you'll shape the infrastructure that enables Surface to ... introduce intelligent AI agents. You'll design systems that support Model Context Protocol (MCP), agent-to-agent communication, and secure LLM-driven experiences at… more
- Google (Mountain View, CA)
- …model development including model training and optimization. + Contribute to model inference optimization in Android Kernel/HAL and in audio and speech ... Senior Research Scientist, Audio Machine Learning _corporate_fare_ Google...validate audio pipelines through both offline simulation and real-time on- device hardware. You will be interacting with partner teams… more
- Walmart (Sunnyvale, CA)
- …next generation of AI powered experiences on smart TVs think on device large language models, real time content understanding, privacy preserving audience insights, ... & train GenAI models targeting CTV use cases: on device LLM quantization, multimodal video text encoders, and diffusion...limited memory devices. + Hands on experience with edge inference (TensorRT, CoreML, TVM, ONNX, TFLite, WebGPU, or similar).… more
- Walmart (Sunnyvale, CA)
- …backend systems and APIs. . Strong understanding of real-time data processing, model inference pipelines, and infrastructure at scale. . Proven success ... vision, architecture, and execution of scalable fraud detection systems, integrating model infrastructure, fraud APIs, internal tools, and platforms. This role plays… more