AI Engineering (LLMs & Applied ML)

What you'll learn

• Explain transformer architectures, attention, and embeddings
• Train, fine-tune, and adapt models with PyTorch, TensorFlow, and Hugging Face
• Evaluate, benchmark, and optimise models for quality and cost
• Integrate LLM APIs from Anthropic, OpenAI, and Google into applications
• Ground models in your own data with embeddings and retrieval
• Apply MLOps to version, serve, monitor, and retrain models
• Deploy AI features reliably to the cloud
• Build AI responsibly with safety, guardrails, and evaluation

Curriculum

1. 01Engineering Foundations for AIClean, tested Python and the software discipline AI systems need
   • Python for AI engineering: typing, packaging, and project structure
   • Clean code, code review, and testing discipline with Pytest
   • Working with APIs, JSON, and asynchronous I/O
   • Version control and collaboration with Git and GitHub
   • Environments, dependencies, and reproducibility

   PythonPytestGit / GitHub
2. 02Deep Learning and Transformer ArchitecturesUnderstand the models from the inside out
3. 03Training and Fine-Tuning ModelsAdapt models to your own problem, the core ML-engineer skill
4. 04Model Evaluation and OptimisationProve quality and make models efficient
5. 05Working with Pretrained Models and LLM APIsRun frontier models and ground them in your data
6. 06MLOps and ProductionRun models reliably across their lifecycle
7. 07Safety, Responsible AI, and CapstoneShip models that are safe, evaluated, and stakeholder-ready

Tools & technologies