Oleksandra Bovkun

OLTP in the Lakehouse: Redefining Data for AI Workloads

Modern AI workloads increasingly demand instant access to up-to-date transactional and analytical data, yet traditional architectures remain siloed, enforcing unnecessary data pipelines. Databricks Lakebase, a new extension to the Lakehouse architecture, brings OLTP capabilities to the platform that already drives ELT, BI, and machine learning. In this talk, we will break down how Lakebase helps create a unified storage layer to enable real-time decisioning, adaptive AI systems, and streaming analytics directly in the Lakehouse. We will unpack the architectural foundations of Lakebase and demonstrate how unifying OLTP and analytics redefines the data stack for AI. Real-world case studies and practical tips will be shared to guide the implementation of a robust data storage layer for production-scale AI workloads.

Oleksandra enjoys sharing her knowledge, experience, and insights about data engineering, data governance, and Databricks. Throughout her career as a Data Engineer and Databricks Solutions Architect, she’s experienced firsthand how challenging it can be to embark on a Data and AI journey. Based on her extensive experience with on-prem to cloud migrations, architecting and implementing data platforms, and running large-scale performance optimization projects with commercial and open source technologies, she is passionate about breaking complex topics and helping the community democratize data and AI for their projects.