Vespa.ai provides the Vespa AI Search Platform, a distributed serving engine that unifies retrieval, ranking, machine learning inference, and real-time serving. The platform combines vector search, lexical search, and structured data search within a single query, serving as infrastructure for business-critical AI applications across web search, recommendation systems, and other AI-driven use cases. A fully managed SaaS version, Vespa Cloud, is also available.
Originally founded in 2001, the company is headquartered in Trondheim, Norway, with a globally distributed team. Its engineering work spans distributed systems, information retrieval, machine learning, vector and lexical search, and retrieval-augmented generation. The platform is designed to handle thousands of queries per second with sub-100-millisecond latency.
Vespa.ai's stated values emphasise technical excellence, transparency, and continuous learning, alongside collaboration and collective accountability.
