01 Python for AI
Python fundamentals NumPy and Pandas Data visualisation (Matplotlib) Jupyter notebooks Virtual environments and packages
Roadmap & Syllabus
AI & Generative AI for Developers Roadmap
AI is now part of everyday development. Learn the foundations of machine learning, then build real applications with large language models — chatbots, semantic search, RAG and agents.
- Python
- NumPy & Pandas
- scikit-learn
- LLM APIs
- Embeddings
- Vector databases
- RAG & Agents
Learning path
Choose where you are today
Each path is written for a different starting point.
Freshers & Students
Starting from the basics and preparing for a first developer job.
Build Python and ML foundations, then your first real AI-powered applications.
Step 1: Python & Data Handling
5 weeksPython fundamentals NumPy and Pandas Cleaning and visualising data
Milestone: Analyse a real dataset and present findings. Step 2: Machine Learning Basics
6 weeksRegression and classification with scikit-learn Evaluation and overfitting Statistics you actually need
Milestone: Train, evaluate and explain a simple model. Step 3: LLMs & Prompting
4 weeksHow LLMs work (intuition) Prompt engineering Calling an LLM API from Python Structured output
Milestone: Build a small LLM-powered tool. Step 4: RAG Project & Interview Prep
5 weeksEmbeddings and a vector database Build a RAG chatbot over documents Deploy with a simple web UI AI/ML interview basics
Milestone: Demo a working “chat with your documents” app.
- House-price or student-result prediction model
- Resume or document summariser using an LLM
- RAG chatbot over a set of PDFs
Complete syllabus
AI & Generative AI for Developers syllabus
Everything this track covers, grouped by topic. Use it as a checklist.
02 Math Essentials
Basic statistics and probability Vectors and matrices (intuition) What gradients and loss functions mean
03 Machine Learning Basics
Supervised vs unsupervised learning Regression and classification Train/test split and overfitting Evaluation metrics scikit-learn
04 Deep Learning (Overview)
Neural networks How transformers work (intuition) PyTorch basics
05 Large Language Models
Tokens, context windows and temperature Prompt engineering Calling LLM APIs Structured output and function/tool calling Cost and latency
06 RAG & Vector Search
Embeddings Vector databases (pgvector, Pinecone, Chroma) Chunking and retrieval Retrieval-augmented generation (RAG)
07 AI Agents & Integration
Tool use and agent loops LangChain / LlamaIndex (overview) Spring AI for Java, LangChain.js for Node.js Streaming responses in a web UI
08 Evaluation & Responsible AI
Testing and evaluating AI output Hallucinations and guardrails Data privacy and security Bias and responsible use
Where it leads
Roles this track prepares you for
- AI Engineer
- Generative AI Developer
- ML Engineer (entry)
- Full Stack Developer with AI skills
Want guidance along the way?
A roadmap tells you what to learn. Guidance helps you learn it in the right depth, practise with real interview questions and explain your projects with confidence.
Explore more
Other roadmaps
Prepare. Perform. Progress.
Turn the AI & Generative AI for Developers roadmap into your plan
Share your background and goals, and we will help you decide what to focus on first.