Skip to content
Try the live demo

Fullstop Learning Course outline

AI Engineering

Build foundations in Python, data and maths, then develop and evaluate ML, deep learning and retrieval-based AI applications.

6 months · 24 weeks · 600 guided course hours. Explore the curriculum, then talk with us about schedule, fees and delivery options.

Ask about this courseBrowse all courses

Course focus

Skills and practice

  • Programming, data analysis, SQL and mathematics
  • Machine learning evaluation, PyTorch and language models
  • LLM applications, retrieval, safety, deployment and capstone

6-part curriculum

A practical path, one module at a time.

Each module follows the supplied course outline. Weekly topics and representative project work are shown below.

  1. Python and Programming Foundations

    Python basics and control flow · Collections, files and errors · Writing maintainable Python · Python project and foundation review

    Practical work: A tested API-data utility with a clear README.

  2. Data Analysis and Mathematics

    NumPy and pandas · SQL and exploratory analysis · Linear algebra and probability · Calculus and optimisation

    Practical work: A repeatable dataset analysis and a NumPy linear-regression implementation.

  3. Machine Learning and Model Evaluation

    The machine learning workflow · Supervised learning algorithms · Metrics, tuning and error analysis · Machine learning project review

    Practical work: A reproducible customer-churn model with evaluation results and error analysis.

  4. Deep Learning and Language Models

    Neural networks and PyTorch · Training and troubleshooting · Computer vision and transfer learning · NLP and transformer foundations

    Practical work: Train and evaluate image and text classifiers; explain model behaviour.

  5. LLM Applications and Retrieval

    Model APIs and prompting · Embeddings and semantic search · Retrieval-augmented generation · Adaptation and application review

    Practical work: Build a document assistant and compare retrieval approaches, latency and cost.

  6. Evaluation, Deployment and Capstone

    Tool calling and bounded workflows · AI quality and security testing · API delivery and operations · Capstone and skills assessment

    Practical work: Deploy an evaluated assistant with an evaluation report, source code and demo.