Interview atlas · current to June 2026

Become the engineer who builds Codex and Claude.

A state-of-the-art training atlas for senior AI engineers. Build agents, workflows, RAGs and fine-tunes like an expert — with live, runnable demonstrations — and answer frontier-lab questions in depth, at every level from IC3 to staff.

4 of 13 pillars live · 18 lessons · built one session at a time
PAPERSLAB ENG BLOGSFRONTIER MODELSPYTORCH · vLLMMCP · AGENTS
LEARNBUILDDRILL
SHIP AGENTSPRODUCTION RAGFINE-TUNE & RLPASS THE LOOP
Pillars live
4/13
depth-first
Lessons
18
runnable + cited
Library resources
197
verified links
Interactive demos
13+
live in lessons

Twelve pillars. Everything a frontier lab tests.

Each pillar ships as a deep, runnable module — first-principles derivations, production tradeoffs, live demos, and a leveled Q&A bank. Depth-first: one polished pillar per session.

016 lessons

ML Foundations (for engineers)

New to ML? Start here. The Stanford/CMU core — how models learn, the math you need, neural nets, the road to LLMs — concise, for software engineers.

Enter →
023 lessons

Building AI Agents

ReAct, planner-executor, tool use, memory, multi-agent and MCP — build a Claude-Code/Codex-style coding agent end to end.

Enter →
035 lessons

RAG & Retrieval

Chunking, hybrid search, rerankers, ColBERT, GraphRAG, contextual retrieval, agentic RAG — and how to evaluate it.

Enter →
044 lessons

Fine-tuning, Post-training & RL

RLHF/RLVR, PPO → GRPO and the variant zoo (DAPO, GSPO, Dr.GRPO…), RL infrastructure, and the 35-question RL interview benchmark, answered.

Enter →
05session 4

AI Workflows & Orchestration

Chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer; workflows-vs-agents and durable execution.

Preview →
06session 5

Inference, Serving & Scaling

vLLM, PagedAttention, KV cache, speculative decoding, quantization (AWQ/FP8), FSDP & tensor/pipeline parallelism.

Preview →
07session 6

Evaluation & Testing

LLM-as-judge, RAGAS/DeepEval, golden datasets, agent trajectory evals and CI regression suites.

Preview →
08session 7

Transformer & DL Foundations

Attention/MHA, RoPE, RMSNorm, activations, tokenization, sampling, and scaling laws — from first principles.

Preview →
09session 8

Context Engineering & Prompting

The context-engineering paradigm, prompt caching, long-context, lost-in-the-middle, structured outputs, CoT.

Preview →
10session 9

Agentic Frontends & Harness Engineering

CopilotKit/AG-UI, generative UI, human-in-the-loop; harness engineering for production coding agents.

Preview →
11session 10

AI System Design

Design a RAG bot over 10M docs, an AI coding agent, an eval platform, a voice assistant, an agentic research system.

Preview →
12session 11

Safety, Alignment & Guardrails

Constitutional AI, RLHF→RLAIF, prompt-injection/jailbreak defense, the 6-layer guardrail stack, red-teaming.

Preview →
13session 12

Interview Mastery

Leveling IC3→staff, OpenAI/Anthropic loops, coding rounds, behavioral/values, and the cross-pillar Q&A bank.

Preview →