Open Source Startup Podcast E186: Unlocking Your Unstructured Data with Typedef
11 snips
Nov 20, 2025 Kostas Pardalis and Yoni Michael, co-founders of Typedef, discuss their journey from major data infrastructure firms to creating solutions for unstructured data. They reveal how traditional systems like Spark fail under current AI demands and introduce Fennec, a tailored DataFrame library for LLMs. Insights on optimizing agentic systems and early go-to-market strategies add depth to their conversation. They also ponder the future of AI in data workflows and critique the explosion of benchmarks in the industry.
AI Snips
Chapters
Transcript
Episode notes
Founders Met Over Coffee
- Kostas and Yoni met on a blind date at Blue Bottle and spent hours brainstorming data infra problems.
- That summer of validation led them to found TypeDef and pursue solutions for brittle data pipelines.
Spark's Assumptions Don't Fit AI Workloads
- Spark was built for different assumptions and struggles with modern AI inference workloads.
- New workloads (unstructured data + inference) need systems that treat inference as a first-class primitive.
Remove Ops Burden Early
- Abstract operational burden so engineers focus on business logic instead of cluster sizing or partitioning.
- Build serverless-style ergonomics to remove ops friction from data teams' workflows.