IT Champion Hub home

AI & Generative AI · AI Engineer

Build, Evaluate and Run AI Applications

Go from the fundamentals of machine learning and large language models to building retrieval-augmented AI applications, and learn how to evaluate, monitor and deploy them responsibly.

  • Machine-learning and LLM fundamentals
  • Embeddings and vector search
  • Retrieval-augmented generation (RAG)
  • Evaluation, monitoring and responsible AI
Enquire About This Course Explore All Training

Course overview

About This Course

AI Engineer covers the skills needed to build practical applications on top of modern AI models, from how models learn to how AI features are evaluated and kept reliable in production.

Organisations are adding AI to search, support, analytics and internal tools. Building these features well takes more than calling a model: engineers need to understand model behaviour, retrieve the right data, measure quality and manage risk.

You will learn the fundamentals of machine learning and large language models, how embeddings and vector search work, how to build retrieval-augmented generation (RAG) applications, and how to evaluate, monitor and deploy AI features responsibly.

This is the broadest of our AI & Generative AI learning paths. Generative AI Development goes deeper into LLM integration, AI Agents & Automation covers multi-step workflows, and AI Security covers how to protect AI applications.

Who it is for

Who Should Take This Course?

  • Software developers

    You build applications and want to add AI features with confidence.

  • Data professionals

    You work with data and want to move into building AI applications.

  • Technologists exploring AI

    You want a structured understanding of modern AI beyond the headlines.

  • Technical leads

    You need to understand how AI systems are built, evaluated and run.

Learning outcomes

What You Will Learn

By working through the course, you will build towards being able to:

  • Explain core machine-learning ideas such as training, features, overfitting and evaluation.

  • Describe how large language models generate text, and their strengths and limitations.

  • Create embeddings and use vector search to find relevant information.

  • Build a retrieval-augmented generation application over a document collection.

  • Integrate AI models into applications through APIs.

  • Evaluate AI output quality with test sets and measurable criteria.

  • Apply responsible AI practices, including bias awareness, transparency and monitoring.

Curriculum

Course Curriculum

The course is organised into modules. Session order and depth may vary by training arrangement.

  1. AI and machine-learning fundamentals

    The ideas behind how models learn from data.

    Topics covered include

    • Supervised and unsupervised learning
    • Training, validation and testing
    • Overfitting and generalisation
    • Common model types

    Practical activity: Train and evaluate a simple model on a sample dataset.

  2. Large language models

    How modern language models work and what they can and cannot do.

    Topics covered include

    • Tokens, context windows and generation
    • Prompting basics
    • Model choice and trade-offs
    • Hallucination and limitations

    Practical activity: Compare model responses to the same task and explain the differences.

  3. Embeddings and vector search

    Represent meaning as numbers and search by similarity.

    Topics covered include

    • What embeddings represent
    • Similarity measures
    • Vector databases and indexes
    • Chunking documents

    Practical activity: Embed a set of sample documents and build a semantic search over them.

  4. Retrieval-augmented generation

    Ground model answers in your own data.

    Topics covered include

    • The RAG architecture
    • Retrieval quality and ranking
    • Prompt construction with context
    • Citing sources

    Practical activity: Build a question-answering assistant over a sample document collection.

  5. AI application development

    Turn AI prototypes into usable application features.

    Topics covered include

    • Model APIs and SDKs
    • Handling errors, latency and cost
    • Structured output
    • Deployment patterns

    Practical activity: Wrap the assistant in a simple application with error handling.

  6. Evaluation, monitoring and responsible AI

    Measure quality and run AI features responsibly over time.

    Topics covered include

    • Building evaluation sets
    • Automated and human evaluation
    • Monitoring in production
    • Bias, transparency and safe use

    Practical activity: Create an evaluation set for the assistant and measure improvements.

Practical learning

Hands-On Learning

Practical work builds an AI application step by step. Examples of activities include:

Some activities use AI model APIs. Whether accounts or API access are provided, or you use your own, will be explained when you enquire.

  • Training and evaluating a simple model
  • Building semantic search with embeddings
  • Creating a retrieval-augmented assistant
  • Evaluating and improving AI output quality

Before you start

Prerequisites and Learning Requirements

  • Recommended background

    Programming experience, ideally in Python, is recommended.

  • Technical prerequisites

    Basic understanding of APIs and data formats such as JSON. Some familiarity with statistics is helpful but not required.

  • Software and tools

    A computer with a reliable internet connection for live online sessions. Python and a code editor are used for practice. Any additional software or accounts for practical activities will be confirmed when you enquire.

  • Prior experience

    Not intended as a first programming course.

Learning Format

IT Champion Hub offers live, instructor-led online training and workshops. Formats, duration and schedules vary by course and are not the same for every program.

  • Live online sessions led by an instructor
  • Practical activities alongside explanations
  • Upcoming batches and schedules shared on enquiry

Enquire to find out the formats and upcoming batches available for this course. Enquire about this course

FAQ

Frequently Asked Questions

Do I need a machine-learning background?

No. The course introduces machine-learning fundamentals before moving to language models and applications. Programming experience is recommended.

Which programming language is used?

Python, the most widely used language for AI development.

Will I need access to AI model APIs?

Some practical activities use AI model APIs. We'll explain how access is arranged, and any costs involved, when you enquire.

How is this different from Generative AI Development?

AI Engineer is broader, covering machine-learning fundamentals, RAG, evaluation and responsible AI. Generative AI Development focuses on integrating LLMs into applications.

How can I enquire about upcoming training?

Select Enquire About This Course. The enquiry form will note that you are asking about AI Engineer, and we'll get back to you with upcoming batches and available schedules.

Ready to Explore This Learning Path?

Have questions about the curriculum, prerequisites, or training arrangements? Get in touch with IT Champion Hub to discuss your learning goals.

Enquire About This Course Explore More Training