Syllabus (2026)

Below is the full 8-week course map (dummy pages for now).

Weeks

Week 01 — Development Environment & Tooling — Set up a modern dev environment and learn the daily tools used by data/AI engineers: editors, packaging, shell, Git, data formats, and lightweight databases.
Week 02 — Deployment & API Engineering — Build and ship real APIs with FastAPI, Docker, auth, observability, and caching. Focus is on production-style services and deployment workflows.
Week 03 — LLM Engineering — Learn prompt + context engineering, structured output, embeddings, search primitives, caching, and evaluation tooling around LLM apps.
Week 04 — RAG & Hybrid RAG — Design retrieval systems: chunking, vector DBs, hybrid search, reranking, grounding, evaluation, and caching for fast reliable RAG.
Week 05 — Agentic AI — Build agent systems: planning loops, tool calling, async execution, LangGraph, MCP servers, multi-agent coordination, and evaluation.
Week 06 — Web Scraping & Data Processing — Scrape, parse, deduplicate, and analyze data: browser automation, crawling, anti-bot strategies, document parsing, DuckDB/Parquet, and multimodal pipelines.
Week 07 — CI/CD, Security & Cloud Infrastructure — Harden and ship: CI/CD pipelines, container security, LLM security + guardrails, cloud compute basics, IaC, budgets, and event-driven systems.
Week 08 — MLOps, Fine-Tuning & Model Publishing — Train, fine-tune, package, publish, and monitor models: data/versioning, MLflow, Vertex AI, HuggingFace, quantization, and responsible model release.

All labs + capstones are listed under Hands-on Labs.