Plumerai makes deep learning radically more efficient, enabling inference on small, inexpensive and low-power hardware. Our technology, powering products such as video doorbell and security cameras, enables the deployment of intelligent, battery-powered sensors everywhere. Our people detection AI consistently proves to be the most accurate for edge devices while consuming minimal resources. Our inference engine for Arm Cortex-M is the fastest and smallest in the world. Our Ikva AI accelerator fits in the smallest of FPGAs. Production-worthy embedded AI requires a relentless focus on the full AI stack, from collecting and curating data to training algorithms, model architectures, inference engines, and hardware optimizations. We have published state-of-the-art research on binarized neural networks at conferences such as NeurIPS and MLSys. Our team is backed by world-class investors with strong backgrounds in deep learning and with track records of founding multi-billion dollar companies.