“Verkada has been building and deploying physical AI before the term existed. With our footprint of more than 2.4 million devices across 170 countries and 30,000 organizations, we’ve proven that the built environment is one of the largest beneficiaries of AI,” said Filip Kaliszan, co-founder and CEO, Verkada. “Working with NVIDIA supercharges what we’ve spent nearly a decade building: AI that keeps students safe in schools, protects workers on factory floors, helps retailers prevent theft, and enables organizations to operate more efficiently.”

Verkada is strengthening the models and data flywheel underpinning its intelligent video analytics through its collaboration with NVIDIA, advancing AI-powered video search, multimodal embeddings and vector retrieval for next-generation semantic search, and synthetic data generation to augment training datasets and improve accuracy.

By leveraging NVIDIA Cosmos world foundation models and NVIDIA Physical AI Data Factory, Verkada has accelerated model training and inference across its expanding global footprint on NVIDIA accelerated computing. Since the collaboration began, Verkada has improved the mean average precision (mAP) of its AI-powered search by 68% for spatial-temporal understanding, delivering faster, more accurate and more robust search capabilities.

Verkada is also developing a multi-model search agent architecture and exploring reasoning models to address complex, unstructured real-world scenarios, from identifying health and safety incidents on a manufacturing floor to detecting shrinkage in retail environments.