Shivam Verma

Shivam Verma is a Spotify machine-learning engineer and AI/recommender-systems researcher focused on personalization, user representations, LLM-aware recommendation, and advertising/podcast targeting systems. He has authored Spotify research on multi-task learning for streaming ads and podcast promotion targeting, and presented “Personalization in the Era of LLMs” at the AI Engineer Summit in London.

Spotify Uses Semantic IDs to Make LLMs Recommend Catalog Items

Spotify’s Shivam Verma argues that LLM-era personalization requires translating both users and catalog items into forms a model can process alongside language. In his account, Spotify combines long-term user embeddings, Semantic IDs that turn tracks and episodes into token sequences, and soft tokens that project a listener’s profile into an LLM’s embedding space. The aim is a generative recommender that can produce catalog-native recommendations without full fine-tuning, while still relying on traditional ranking layers for production use.

AI EngineerMay 19, 202610 min read