Verkada and NVIDIA are collaborating to accelerate physical AI development, enhancing AI-powered video analytics and search capabilities for security and operations.
Verkada announced a collaboration with NVIDIA to accelerate the development and deployment of physical AI for the built environment, while NVIDIA also joins the company as a new investor following a strategic investment from Alphabet's CapitalG announced at the end of last year.
The collaboration is intended to advance Verkada's AI-powered physical security and operations platform, which the company says helps organizations including schools, hospitals, retailers and manufacturers transform operational data into actionable intelligence that supports safety and operational efficiency.
According to Verkada, the company has deployed more than 2.4 million devices across 170 countries and serves more than 30,000 organizations.
"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 of 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."
As part of the collaboration, Verkada is strengthening the models and data flywheel behind its intelligent video analytics platform. The work includes advancing AI-powered video search, multimodal embeddings, vector retrieval for semantic search and synthetic data generation to expand training datasets and improve model accuracy.
Verkada said it is using NVIDIA Cosmos world foundation models and NVIDIA Physical AI Data Factory to accelerate model training and inference across its global deployment using NVIDIA accelerated computing.
The company said the collaboration has already improved the mean average precision (mAP) of its AI-powered search by 68% for spatial-temporal understanding, resulting in faster, more accurate and more robust search capabilities.
Verkada is also developing a multi-model search agent architecture and exploring reasoning models designed to address complex, unstructured scenarios, including identifying health and safety incidents in manufacturing environments and detecting shrinkage in retail settings.
The company said the collaboration reflects its broader effort to develop more capable, context-aware AI designed to improve the resilience and safety of built environments.