genai.college · Learn · Leagues · Advertise

Course map

Prompt Engineering and API Integration

Learn how large language models are offered as platforms, how to talk to them well, and how to wire them into real software through APIs.

1. Foundations & Overview of GenAI Platforms
2. Basics and Advanced Prompt Engineering Techniques
3. API Integration with LLMs
4. Advanced Handling of LLM Responses
5. Conversational Interfaces with LLMs
6. Function Calling & Tool Integration
7. Understanding and Evaluating Generative AI Outputs

Basics of NLP and RAG

Ground model answers in your own documents. Learn how text becomes vectors, how vector search works, and how to build Retrieval-Augmented Generation pipelines.

1. Introduction to RAG & Text Representation
2. Building Blocks of RAG
3. Vector Databases
4. Building a Basic RAG Pipeline
5. RAG using LangChain and LlamaIndex
6. Advanced RAG Topics

AI Agents and Multi-Agent Systems

Move from single prompts to systems that plan, use tools, remember and collaborate. Build with LangGraph, MCP and agentic RAG.

1. Foundation of Agents
2. Building Blocks of AI Agents
3. Memory in AI Agents
4. Agent Architecture & Design Patterns
5. Intro and How to Build Multi-Agent Systems (MAS)
6. Three C's: Communication, Coordination & Cooperation in MAS
7. AI Communication Protocols & Building an MCP Server
8. Introduction to LangGraph
9. Entering into Agentic AI
10. Tool Orchestration: Building Agentic RAG (LangChain + LangGraph)
11. Agent Evaluation & Debugging

Deployment and Project Integration

Take GenAI prototypes to production: APIs, containers, cloud hosting, CI/CD, monitoring and the LLMOps lifecycle.

1. Introduction to Deployment & LLMOps Lifecycle
2. Building APIs with FastAPI
3. Understanding Containerization with Docker
4. Deploying GenAI Apps via Hugging Face Spaces and Intro to GCP
5. Automating Deployment with CI/CD
6. Orchestrating Modular GenAI Systems
7. Monitoring & Securing GenAI Systems
8. Advanced Deployment, Scaling & LLMOps

AI Solution Architecture & Consulting (FDE)

Think like a Forward Deployed Engineer: work with clients, discover real problems, design GenAI solutions and deliver measurable value.

1. The Forward Deployed Engineer Role
2. Discovery & Requirements Gathering
3. Solution Architecture Patterns
4. Build vs Buy & Model Selection
5. Cost Estimation & ROI
6. Stakeholder Communication & Delivery

AI-Assisted Development with Agentic IDEs

Use AI coding agents as everyday tools: set them up, give them good context, run plan–build–test loops and review their work safely.

1. What Agentic IDEs Are
2. Setting Up Your Environment
3. Context, Rules and Project Instructions
4. Agentic Workflows: Plan, Build, Test
5. Reviewing AI-Generated Code & Security
6. Team Practices & Productivity

Foundations of Neural Networks and Transformers

Build the math and intuition behind modern models: vectors, derivatives, gradient descent, neural networks, and the networks used for text and images.

1. Linear Algebra; Calculus
2. Other Mathematical Topics: Learning with Derivatives
3. Foundations of NN: Gradient Descent
4. Building a Neural Network
5. How Neural Networks Work
6. Neural Networks Advanced
7. Neural Networks for Text
8. Convolutional Neural Networks

Fine-Tuning LLMs

Adapt models to your domain: small language models, data strategy, parameter-efficient fine-tuning, alignment, quantisation and safe lifecycle management.

1. Introduction to SLMs
2. Domain Data Strategy
3. Efficient Fine-Tuning (PEFT)
4. Domain-Adaptive Pre-Training (DAPT)
5. Supervised Fine-Tuning (SFT) Implementation
6. Reasoning & Style Alignment
7. RAG-Aware Behaviour & Hallucination Control
8. Quantization & Deployment
9. Safety, Evaluation & Lifecycle Management

About · Contact · Privacy · Terms