Blog
Deep dives into ML systems, training, and inference.
Free12 min read
A Gentle Introduction to verl — Part 1
Wrangle and implement RL algorithms with confidence. A deep dive into verl's architecture — from master-worker design to the PPO training loop — so you can go beyond config files.
reinforcement-learningverlinfrastructure
Free15 min read
Absolute Zero Reasoner: Walkthrough, Implementation and No Jargon
How to make your LLM learn math and code using *no* data. A no-jargon deep dive into AZR — the paper that eliminates alignment data by having the model propose and solve its own problems.
reinforcement-learningreasoningpost-training
Free8 min read
You Have Been Doing ML System Design Interviews Wrong
The questions you should ask, before you even begin. ML System Design interviews aren't about showcasing the latest research — they're a sophisticated vibe check.
interviewssystem-designcareer