Generative AI & LLM Development
Move from using AI tools to building with them: how large language models work, provider APIs, embeddings and retrieval, AI agents, and shipping a real generative AI application.
4 modules · 12 lessons
01
Understanding LLMs
- How large language models work
- Tokens, context and limitations
- Choosing the right model for a task
02
Prompt Engineering and APIs
- Prompt engineering: structured, few-shot and chain-of-thought techniques
- Working with OpenAI, Anthropic and open-source model APIs
- Handling responses and errors
03
Embeddings, RAG and Vector Databases
- What embeddings represent
- Vector search with FAISS, Pinecone or Chroma
- Building a RAG pipeline with LangChain or LlamaIndex
04
Building AI Agents
- Agent architectures and tool use
- Connecting agents to real APIs
- Shipping a working GenAI application
Before and after this course.
Before you begin
- Comfort writing basic Python
- Completion of Python for AI & Data or equivalent experience
- A provider API key (guidance provided)
What this actually builds
- Build a working retrieval-augmented application
- Design a basic AI agent for a real task
- Understand the tradeoffs behind production GenAI systems
Certificate of Completion
Earn recognition upon course completion
Receive a certificate upon meeting the program's completion criteria. Add it to LinkedIn or your resume as a record of what you built.
Certificate of Completion
Generative AI & LLM Development
- Shareable on LinkedIn and social media
- Verifiable by employers and institutions
- Includes course completion details and skills
Reflects real work
Tied to modules and projects you actually complete
Completion-based
Issued only when the completion criteria are met
Shareable
Add it to LinkedIn or your resume