Deep Dives on Apache Spark

Apache Spark powers most of the world's data and AI pipelines — and quietly eats a big share of the cloud bill. We show you where it goes and how to get it back.

Spark is the most-used engine in data and AI, and often the most poorly handled: in the rush to ship, its real capability gets overlooked. We're changing that.

Every video opens a real production job, finds what's actually slow or expensive and shows the fix — engineer to engineer.

WHAT YOU'LL TAKE AWAY
▸ Faster jobs — Spot skew, spill, bad partitioning and shuffle blowups in the Spark UI
▸ A bill you can explain — What one job really costs and how to bring it down
▸ Confidence in production — Build & Debug actual production jobs like a pro
▸ The internals that matter — How the engine works and interesting internals

For Data, Platform and AI/ML Engineers, Architects and anyone who owns a Spark bill.

New episode Every Week 🫡

By Quanton, a drop-in execution engine for Apache Spark™ from Onehouse → https://quanton.dev/