Engineering teams globally are building AI applications or integrating AI features into existing products. The AI development ecosystem is maturing, accelerating the prototyping of these applications. However, moving AI applications to production remains notoriously complex. Modern AI stacks require LLMs, embeddings, vector search, observability, new caching layers, and continuous adaptation to the rapidly shifting landscape. The data layer increasingly serves as both foundation and bottleneck in AI app productionization.
MongoDB is expanding beyond its core document database into a comprehensive AI-ready database platform with capabilities for operational data, search, real-time analytics, and AI-powered data retrieval. The company recently acquired Voyage AI to offer users accurate and cost-effective embedding models and rerankers.
Fred Roma, a veteran engineer and currently SVP of Product and Engineering at MongoDB, joins the show with Kevin Ball to discuss AI application development, vector search and reranking, schema evolution in the LLM era, the Voyage AI acquisition, and the evolution of data platforms to keep pace with AI’s rapid advancements.
Full Disclosure: This episode is sponsored by MongoDB.
Kevin Ball, also known as KBall, is Vice President of Engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and was CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.
Please click here to see the transcript of this episode.