https://www.infoq.com InfoQ Products feed https://www.infoq.com/news/2026/03/doordash-semantic-search/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Products <img src="https://res.infoq.com/news/2026/03/doordash-semantic-search/en/headerimage/generatedHeaderImage-1772917454999.jpg"/><p>DoorDash has launched a multimodal machine learning system that aligns product images, text, and user queries in a shared embedding space. Trained on 32 million labeled query-product pairs using contrastive learning, the system improves semantic search, product ranking, and advertising relevance. Embeddings also support other machine learning tasks across the marketplace.</p> <i>By Leela Kumili</i> Online Learning Machine Learning Embedded-Databases commercial-off-the-shelf vector databases Offline-First Search E-Commerce Rankings Products Architecture & Design AI, ML & Data Engineering Development news Mon, 16 Mar 2026 14:25:00 GMT https://www.infoq.com/news/2026/03/doordash-semantic-search/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Products Leela Kumili 2026-03-16T14:25:00Z /news/2026/03/doordash-semantic-search/en