The framework that powers Tesla Autopilot, Meta AI, and most ML research. Start with tensors, build CNNs and Transformers from scratch, then deploy your model as a production API. Every lesson has a hands-on notebook.
What You Build
An end-to-end ML-powered application: custom model trained in PyTorch, served via TorchServe, with a working frontend
Sections
Lessons
Estimated
Concepts
TensorFlow, JAX & the Google AI Stack
Google builds more ML infrastructure than anyone. Learn TensorFlow + Keras for production, JAX for research-speed training, TPUs for scale, and Vertex AI for deployment. Plus the Gemini API for multi-modal AI.
Meta AI & Open Source ML
Meta has open-sourced more AI than any company: Llama, FAISS, SAM, Detectron2. Learn to run LLMs locally, fine-tune with LoRA, build vector search, and deploy RAG pipelines — all with zero API costs. Plus Microsoft ONNX, Hugging Face, and MLflow.
ML Engineering for Principal Engineers
You don't need to train models — you need to design the systems that train, serve, monitor, and scale them. GPU infrastructure, cost optimization, model serving patterns, ML CI/CD, security, team topology, and incident response. The system design interview for ML, but practical.
Dev Jordan
walkthrough · casual
First 4 lessons are free (29% of the course). No login required.