Mayank Sethi

Mayank Sethi

Mayank Sethi

Principal Database Engineer, Group 1001

Title of Talk:

Beyond "Throw an LLM at It": Tiered Computational Intelligence for Classifying 1.5 Million Columns of Enterprise Data


Abstract

As enterprises consolidate decades of legacy systems into cloud data platforms, data governance faces a scale problem: how do you accurately classify millions of columns of sensitive data without an army of analysts — and without surrendering judgment entirely to a black-box model? This keynote presents the architecture and lessons from a production system that classified over 1.5 million columns across 62 databases in nine days, built and deployed by a single engineer. The system uses a tiered classification engine that applies deterministic, institution-aware rules first, native statistical classification second, and reserves large language model inference for only the truly ambiguous minority of columns — cutting cost by an order of magnitude while suppressing the over-classification that makes naive LLM tagging unusable at scale. Equally important is what surrounds the models: a human-in-the-loop review workflow that lets domain experts correct the engine without writing SQL, with corrections flowing back into production tags in about a minute. The talk argues for a design philosophy of "automation that serves experts, not replaces them," and offers a practical blueprint for regulated industries — finance, insurance, healthcare, where governance must be simultaneously fast, auditable, and trustworthy.


Brief Profile
Mayank Sethi is a Principal Database Engineer at Group 1001, a US financial services and insurance organization, where he leads data platform modernization and enterprise data governance. Over more than a decade in financial services — including five years at PIMCO, one of the world's largest investment managers — he has specialized in large-scale data migration, cloud data architecture, and automated PII/SPI classification. He is an IEEE Senior Member, a published IEEE author, a SnowPro Advanced Architect, and holds three AWS certifications. His recent work on AI-driven data classification, which tagged over 1.5 million columns of enterprise data in nine days, was featured by Dagster and has been recognized by industry leaders in data engineering. He writes regularly on data architecture and governance, and serves as a peer reviewer for international conferences and journals.