Generative AI & Prompt Engineering.

1. 01

   Foundations of Generative AI

   From machine learning to generative AI · How large language models work · Tokens, context windows and limitations

2. 02

   Prompt Engineering Techniques

   Zero-shot and few-shot prompting · Chain-of-thought and role prompting · Prompt templates and iteration

3. 03

   Python & LLM APIs

   Python essentials for AI · Calling LLM APIs · Managing cost, latency and rate limits

4. 04

   Structured Outputs & Function Calling

   JSON and schema-based outputs · Tool and function calling · Error handling and retries

5. 05

   Embeddings & Vector Databases

   Text embeddings and similarity search · Vector databases (Chroma, Pinecone, pgvector) · Chunking strategies

6. 06

   Retrieval-Augmented Generation (RAG)

   RAG architecture · Building RAG with LangChain and LlamaIndex · Improving retrieval quality

7. 07

   AI Agents & Workflows

   Agent design patterns · Tool use and multi-step workflows · Model Context Protocol (MCP) basics

8. 08

   Multimodal AI & Image Generation

   Vision and document understanding · Image generation tools · Speech-to-text and text-to-speech

9. 09

   Evaluation, Safety & Deployment

   Evaluating LLM outputs · Guardrails and responsible AI · Deploying GenAI apps with FastAPI and Streamlit

10. 10

    Capstone: Build a Generative AI Application

    Defining the use case · Building and evaluating the app · Deploying and demoing the solution

Companies hiring for these roles