🎓 Stanford AI Engineer Roadmap 2026

📐 Mathematics → 🤖 Machine Learning → 🧠 Deep Learning → 💬 LLMs → 🏭 Production AI Systems

A free, self-study path built entirely from Stanford's publicly available courses. Every course lists its ID, what it covers, where to find the slides, and a direct link to the official lecture videos where one exists.

📌 How to use this: Watch lectures + do the public assignments. ~70% depth per stage is enough to advance. Whole path ≈ 9–14 months part-time. Follow the main sequence; use the branches by interest.

---

Stage 0 — Mathematics & Foundations 📐

Build the mathematical foundation every AI engineer needs.

ID	Course	Covers	Lecture Slides	Playlist
MATH51	LINEAR ALGEBRA & MULTIVARIABLE CALCULUS	Vectors, matrices, transformations, gradients, integrals	Site	No public video — use MIT 18.06 (Strang)
CS109	PROBABILITY FOR COMPUTER SCIENTISTS	Probability, random variables, distributions, Bayes, inference	Site	▶️ YouTube (2022)
EE364A	CONVEX OPTIMIZATION I (BOYD)	Convex sets/functions, optimization, duality, gradient methods	Slides	▶️ YouTube (2023)

---

Stage 1 — Machine Learning 🤖

The classical ML core that underpins modern AI.

ID	Course	Covers	Lecture Slides	Playlist
CS221	ARTIFICIAL INTELLIGENCE	Search, reasoning, logic, planning, decision-making	Site	▶️ YouTube (2019)
CS229	MACHINE LEARNING	Supervised & unsupervised learning, statistical learning, RL basics	Notes	▶️ YouTube (2022)
CS229M	MACHINE LEARNING THEORY	Generalization, VC dimension, PAC learning, bounds, guarantees	Site	No public video — notes only
CS228	PROBABILISTIC GRAPHICAL MODELS	Bayesian networks, Markov models, inference, structure learning	Site	No Stanford playlist — Koller PGM (Coursera)

---

Stage 2 — Deep Learning & Decision Making 🧠

Neural networks, perception, reinforcement learning, and decision making.

ID	Course	Covers	Lecture Slides	Playlist
CS230	DEEP LEARNING	Neural nets, backprop, optimization, regularization, training strategy	Lectures	▶️ YouTube (2018)
CS231n	DEEP LEARNING FOR COMPUTER VISION	CNNs, vision transformers, detection, segmentation, generative models	Site	▶️ YouTube (2025)
CS234	REINFORCEMENT LEARNING	MDPs, value/policy learning, deep RL, exploration	Site	▶️ YouTube (2024)
CS238	DECISION MAKING UNDER UNCERTAINTY	MDPs, POMDPs, decision theory, estimation, control	Site	No public video — free textbook + slides

Advanced sequential decision-making continues in CS239 (AA229) if you want to go deeper.

---

Stage 3 — LLMs & Generative AI 💬

From NLP fundamentals to building and training large language models.

ID	Course	Covers	Lecture Slides	Playlist
CS224N	NLP WITH DEEP LEARNING	Word embeddings, attention, transformers, LLM foundations	Site	▶️ YouTube (2024)
CS224U	NATURAL LANGUAGE UNDERSTANDING	Semantics, dialogue systems, meaning & grounding	Site	▶️ YouTube (2023)
CS25	TRANSFORMERS UNITED	Foundation models, transformer architectures, multimodal, scaling	Site	▶️ YouTube
CS324	LARGE LANGUAGE MODELS	LLM theory, scaling, capabilities, harms, evaluation	Notes & readings	No public video — notes only
CS336 ⭐	LANGUAGE MODELING FROM SCRATCH	Tokenization, transformer impl, GPUs/Triton, parallelism, inference, scaling laws	Site · Repo	▶️ YouTube (2025)

---

Stage 4 — AI Systems & Production 🏭

Build, deploy, and operate AI systems in the real world.

ID	Course	Covers	Lecture Slides	Playlist
CS329S	MACHINE LEARNING SYSTEMS DESIGN	MLOps, model serving, monitoring, A/B testing, evaluation, scaling	Syllabus	No full playlist — Demo Day + guest tutorials
CS329T	TRUSTWORTHY ML: LLMS & APPLICATIONS	RAG, agentic AI, evaluation, reliability, responsible deployment	Site	No public video — slides only

Note: CS329S last ran Winter 2022 — strong on classic MLOps, pre-LLM. CS329T is the modern complement: it's the only course on this roadmap that teaches RAG and agentic AI directly. For anything beyond the courses ( fine-tuning workflows, vLLM/Triton serving, vector DBs), Chip Huyen's AI Engineering (O'Reilly, 2024) is the current reference.

---

🦾 Optional — Robotics Track

For autonomy / robotics roles. Tangential to a generic AI-engineering path. Both are slides-only (no public video).

ID	Course	Covers	Lecture Slides	Playlist
CS237A	PRINCIPLES OF ROBOT AUTONOMY I	Perception, localization, planning, control	Site	No public video — slides only
CS237B	PRINCIPLES OF ROBOT AUTONOMY II	RL, manipulation, imitation learning, human intent inference	Site	No public video — slides only

---

🗺️ Suggested Sequence

Main path: Math → ML → Deep Learning → LLMs → Production

MATH51 / CS109 / EE364A
        │
      CS229 ──► CS229M ──► CS228
        │
      CS230 ──┬── CS231n         (Vision)
              ├── CS234 ──► CS238 (RL / decision-making)
              └── CS224U          (Language)
        │
   converge ►  CS224N ──► CS25 ──► CS324 ──► CS336
        │
      CS329S ──► CS329T          (Production)

Optional branch:  CS237A ──► CS237B   (Robotics)

---

🔗 Master Link Reference

ID	Course	Site	Video
MATH51	LINEAR ALGEBRA & CALCULUS	https://web.stanford.edu/class/math51/	No public video — use MIT 18.06 (Strang)
CS109	PROBABILITY	https://web.stanford.edu/class/cs109/	▶️ YouTube (2022)
EE364A	CONVEX OPTIMIZATION	https://ee364a.stanford.edu/	▶️ YouTube (2023)
CS221	ARTIFICIAL INTELLIGENCE	https://web.stanford.edu/class/cs221/	▶️ YouTube (2019)
CS229	MACHINE LEARNING	https://cs229.stanford.edu/	▶️ YouTube (2022)
CS229M	MACHINE LEARNING THEORY	https://cs229m.stanford.edu/	No public video — notes only
CS228	PROBABILISTIC GRAPHICAL MODELS	https://web.stanford.edu/class/cs228/	No Stanford playlist — Koller PGM (Coursera)
CS230	DEEP LEARNING	https://cs230.stanford.edu/	▶️ YouTube (2018)
CS231n	DEEP LEARNING FOR CV	https://cs231n.stanford.edu/	▶️ YouTube (2025)
CS234	REINFORCEMENT LEARNING	https://web.stanford.edu/class/cs234/	▶️ YouTube (2024)
CS238	DECISION MAKING UNDER UNCERTAINTY	https://web.stanford.edu/class/cs238/	No public video — free textbook + slides
CS224N	NLP WITH DEEP LEARNING	https://web.stanford.edu/class/cs224n/	▶️ YouTube (2024)
CS224U	NATURAL LANGUAGE UNDERSTANDING	https://web.stanford.edu/class/cs224u/	▶️ YouTube (2023)
CS25	TRANSFORMERS UNITED	https://web.stanford.edu/class/cs25/	▶️ YouTube
CS324	LARGE LANGUAGE MODELS	https://stanford-cs324.github.io/	No public video — notes only
CS336	LM FROM SCRATCH	https://cs336.stanford.edu/	▶️ YouTube (2025)
CS329S	ML SYSTEMS DESIGN	https://stanford-cs329s.github.io/	No full playlist — Demo Day + guest tutorials
CS329T	TRUSTWORTHY ML: LLMS & APPS	https://web.stanford.edu/class/cs329t/	No public video — slides only
CS237A	PRINCIPLES OF ROBOT AUTONOMY I	https://web.stanford.edu/class/cs237a/	No public video — slides only
CS237B	PRINCIPLES OF ROBOT AUTONOMY II	https://web.stanford.edu/class/cs237b/	No public video — slides only

▶️ = full official lecture playlist, verified. 11 of these 20 courses have public Stanford video; the other 9 were never recorded publicly (slides/notes only, or Canvas-restricted) — those rows point to the best legitimate substitute instead of a fake link.

---

✨ All courses are free to audit via lecture videos or notes. Enrolled/certificate versions are available through Stanford Online and the Stanford AI Professional Program. 🎯 Follow the sequence. Build projects. Master AI engineering.