Free · Self-paced · No signup
Learn how modern AI systems actually work
Not tutorials that wrap an API call. Close readings of the papers and production systems behind LLM inference, distributed systems, fine-tuning, and agents — from someone who's built them at scale.
45 lessons · 5 tracks · progress saved automatically · always free
Grounded in the papers
Every lesson is a close reading of the actual paper — the mechanism, the numbers that matter, and the claims that don't survive production.
Production-tested
Written from real systems work (Ashwani Jha — ex-Amazon: Just Walk Out, Pay, AWS CloudFormation). Every topic includes when not to use it.
Yours to pace
Read on the web or get it as a daily email. Your progress is tracked in the browser — no account, no paywall to start.
Choose a track
LLM Inference & Serving
10 lessons · ~2hHow large language models actually run in production — KV-cache management, batching, speculative decoding, quantization, and the systems work that turns a model into a serveable endpoint.
Distributed Systems
7 lessons · ~2hFoundational papers and production lessons on storage, consensus, replication, and large-scale data infrastructure — the substrate everything else runs on.
Fine-Tuning & Adaptation
7 lessons · ~2hAdapting pre-trained models to your task without burning a cluster — LoRA and its variants, quantized training, and the tradeoffs that decide quality.
AI Agents & Reasoning
1 lesson · ~1hGetting LLMs to plan, use tools, remember, and reason — what the agent papers actually demonstrate and how the patterns hold up in production.
Paper Breakdowns
20 lessons · ~4hThe “What the Paper Actually Says” series — close readings of the systems and ML papers that matter, focused on the mechanism, the numbers, and when not to use the idea.
Prefer it in your inbox?
Get the LLM Inference track as a free 14-day email course — one short, self-contained lesson a day.