AI Engineer

What you will learn

• How computers, data, and the internet work for AI
• Python from scratch: variables, logic, functions, loops
• Working with data using Python and libraries like NumPy and pandas
• Set up your AI development environment (Python, Jupyter, VS Code)
• Use Git and GitHub to save and share your work

Hands-on labs

• Set up your own AI development environment
• Write your first Python programs
• Explore a real dataset with pandas in a Jupyter notebook
• Push your first project to GitHub

What you will learn

• The maths behind AI, explained simply (just what you need)
• Supervised and unsupervised learning
• Building models: regression, classification, clustering
• Training, testing, overfitting, and evaluation
• Using scikit-learn to build real models

Hands-on labs

• Build a regression model to make predictions
• Build a classification model and measure its accuracy
• Handle a messy real dataset and prepare it for modelling
• Evaluate and improve a model

What you will learn

• What neural networks are and how they learn
• Building neural networks with TensorFlow and PyTorch
• Training deep models: layers, activation, backpropagation
• Computer vision basics with convolutional networks
• Working with GPUs and training at scale

Hands-on labs

• Build and train your first neural network
• Build an image classifier with a convolutional network
• Train a model on a GPU
• Tune a deep learning model for better results

What you will learn

• Natural language processing fundamentals
• Tokenisation, embeddings, and how AI represents meaning
• The transformer architecture that powers modern AI
• How large language models are trained and how they generate text
• Using Hugging Face and running open-source models

Hands-on labs

• Build a basic NLP pipeline
• Explore embeddings and how meaning is represented
• Run an open-source LLM on your own machine with Ollama
• Use Hugging Face models for real tasks

What you will learn

• Prompt engineering patterns: few-shot, chain-of-thought, function calling
• Working with LLM APIs (OpenAI, Anthropic, Google)
• Building LLM apps with LangChain
• Structured outputs, guardrails, and evaluation
• Building interfaces with Streamlit and Gradio

Hands-on labs

• Design and test prompts for real tasks
• Build an LLM-powered app with an API
• Use LangChain to build a multi-step app
• Ship an app with a working interface

What you will learn

• What RAG is and why every company wants it
• Embeddings and semantic search
• Vector databases: Pinecone, Chroma, FAISS
• Building a RAG pipeline end to end
• Evaluating and improving RAG quality, and advanced RAG

Hands-on labs

• Build embeddings from your own documents
• Set up and query a vector database
• Build a working RAG application over your own data
• Evaluate and improve your RAG system

What you will learn

• Building AI agents with tools and function calling
• Multi-agent systems and agent workflows
• Model Context Protocol (MCP) for connecting agents to tools and data
• MLOps: deploying, serving, and monitoring models
• Managing cost, performance, and reliability in production

Hands-on labs

• Build an AI agent that uses tools to complete a task
• Build a multi-agent workflow
• Deploy an AI service to the cloud
• Set up monitoring for a deployed model

What you will learn

• Design and build a complete, production-style AI system (capstone)
• Assemble a portfolio spanning ML, deep learning, LLMs, RAG, and agents
• Learn to talk confidently about the full AI stack in interviews
• Get your CV and LinkedIn profile reviewed
• Practise with technical and competency-based mock interviews

Hands-on labs

• Design and build a complete, production-style AI system drawing on the whole programme: a trained model or fine-tuned LLM, a RAG pipeline over real data, agent capabilities, a user interface, and live deployment with monitoring
• Reviewed and signed off by a senior practitioner, it becomes the centrepiece of your portfolio