Whether you’re an ML engineer, data architect, or AI leader, get a proven framework to identify and overcome critical data challenges.
talk-data.com
Speaker
Nir Ozeri
2
talks
Senior Software Engineer
lakeFS
Nir Ozeri is a Core Committer and Maintainer at lakeFS, with experience across the tech stack from firmware to cloud-native systems. Using a Git-like model, lakeFS brings software engineering best practices to data, AI and ML projects – enabling safe development and testing, early error detection, and reproducible results. As a core developer at lakeFS, Nir has been instrumental in the architecture and development of many of lakeFS's most significant features, helping shape lakeFS into the powerful platform it is today.
Bio from: Big Data LDN 2025
Filter by Event / Source
Talks & appearances
2 activities · Newest first
Most enterprise AI initiatives don’t fail because of bad models. They fail because of bad data. As organizations rush to integrate LLMs and advanced analytics into production, they often hit a roadblock: datasets that are messy, constantly evolving, and nearly impossible to manage at scale.
This session reveals why data is the Achilles’ heel of enterprise AI and how data version control can turn that weakness into a strength. You’ll learn how data version control transforms the way teams manage training datasets, track ML experiments, and ensure reproducibility across complex, distributed systems.
We’ll cover the fundamentals of data versioning, its role in modern enterprise AI architecture, and real-world examples of teams using it to build scalable, trustworthy AI systems.
Whether you’re an ML engineer, data architect, or AI leader, this talk will help you identify critical data challenges before they stall your roadmap, and provide you with a proven framework to overcome them.