COMP429 AI Systems Engineering

Computing & Information Systems · Systems engineering

COMP429 AI Systems Engineering and Intelligent Applications

You know how to build models. Now learn how to build systems. Design, integrate, deploy and govern enterprise-scale AI solutions — retrieval- augmented generation, agentic architectures, multimodal applications and the operational discipline that keeps them running.

Explore the curriculum View syllabus
8 modules 24 units 197 tutorial pages 15 credits

Course overview

From models to intelligent systems

COMP429 teaches the engineering, integration, deployment, governance and real-world application of intelligent systems. It introduces no new learning algorithms — its subject is how to build with the ones you already know.

After COMP329 you can train a transformer, fine-tune a foundation model and implement a reinforcement learning agent. What you have not yet done is assemble those components into a complete, reliable, production-grade system that an organisation can depend on.

That is the gap this course closes. You will learn to design end-to-end AI architectures, build retrieval-augmented and agentic applications, integrate foundation models into business software, and operate AI systems at scale with proper monitoring, evaluation and governance.

The emphasis throughout is on engineering judgement: choosing between architectures, managing cost and latency, handling failure gracefully, and knowing when a simpler solution is the right one. The course culminates in a production-ready intelligent application built to enterprise standards.

Prerequisites

COMP329 Advanced Machine Learning and Deep Learning, or equivalent. You should already be able to train and evaluate neural networks, work with pretrained transformers, and write well-structured Python.

No new algorithms

COMP429 deliberately introduces no new machine learning theory. Every unit is about architecture, integration, engineering practice or governance — the skills that turn models into systems.

Course details

Level
Undergraduate · Final year / advanced
Credits
15 credits, one semester
Delivery
2 lectures and 1 engineering studio session per week, plus project work
Language & tools
Python, LangChain / LlamaIndex, vector databases, cloud AI platforms, Docker
Assessment
6 assignments, 24 unit quizzes, midterm, final exam and a major capstone
RAG Agentic AI Multimodal LLMOps
Course structure at a glance
Module Focus Units Tutorials
1 · AI Systems Engineering Foundations Systems thinking, AI architectures and engineering AI projects 3 24
2 · Foundation Models & LLM Engineering Model ecosystems, prompting at scale and LLM application engineering 3 25
3 · Retrieval-Augmented & Knowledge-Based AI Information retrieval, RAG architecture and enterprise knowledge systems 3 25
4 · Agentic AI & Multi-Agent Systems Agent architectures, collaboration and workflow orchestration 3 25
5 · Multimodal Intelligent Systems Cross-modal foundations, vision-language systems and conversational AI 3 24
6 · AI Deployment & Operations Cloud AI platforms, LLMOps/MLOps and observability 3 25
7 · Trustworthy Enterprise AI Governance, human-centred design and AI security 3 25
8 · Designing Real-World Intelligent Applications Industry solutions, AI product development and integrated system design 3 24
Total Eight modules · twenty-four units 24 197

Curriculum position

Where COMP429 fits

COMP429 is the fifth course in the sequence, bridging advanced machine learning and AI research. It assumes COMP329 and prepares you for COMP529.

  1. COMP326 · Data Science Foundations
  2. COMP327 · Generative AI
  3. COMP328 · Machine Learning
  4. COMP329 · Advanced ML & Deep Learning
  5. COMP429 · AI Systems Engineering
  6. COMP529 · Research Topics in AI

Learning outcomes

What you will be able to do

On successful completion of COMP429 you will be able to engineer, deploy and govern complete AI systems at enterprise scale.

AI systems design

  • Design end-to-end AI system architectures.
  • Integrate machine learning models into software systems.
  • Design scalable, resilient AI pipelines.

AI engineering

  • Build agentic AI systems with planning and tool use.
  • Develop retrieval-augmented generation applications.
  • Integrate foundation models into business applications.
  • Develop multimodal AI solutions.

Deployment

  • Deploy AI systems using cloud infrastructures.
  • Monitor and maintain AI applications in production.
  • Implement MLOps and LLMOps workflows.

Governance

  • Evaluate AI risks and governance requirements.
  • Design trustworthy and reliable AI systems.
  • Implement human-in-the-loop solutions.

Professional practice

  • Deliver enterprise-quality AI solutions.
  • Communicate technical and strategic AI decisions.
  • Work to professional engineering and documentation standards.

Integrated capability

  • Select appropriate architectures for a given problem and constraint.
  • Balance cost, latency, quality and reliability trade-offs.
  • Evaluate complete systems, not just individual models.

Curriculum

Eight modules, twenty-four units

Each unit is delivered as a sequence of tutorial pages: architecture diagrams, implementation examples, industry case studies, hands-on activities and a knowledge check.

How it works

Engineering, not just implementing

Every unit follows the same four-part structure, moving from architecture through to a working, evaluated component.

  1. Study the architecture

    Start with the system diagram: what the components are, how they communicate and why the design was chosen.

  2. Build the component

    Implement the pipeline, agent, retriever or deployment step using industry tooling.

  3. Evaluate in context

    Assess the whole system — cost, latency, quality, failure modes — not just the model.

  4. Check your understanding

    Finish with knowledge checks, a unit quiz and a short architectural reflection.

Assessment

How your work is assessed

Assessment is dominated by engineering work. Six assignments build towards the capstone, with quizzes and exams confirming conceptual understanding.

35%

Major capstone

A complete enterprise intelligent application, designed, built, deployed and evaluated.

30%

Six assignments

Architecture, RAG, agentic AI, multimodal, AI operations and governance.

15%

Final exam

Cumulative, with an emphasis on architecture reasoning and trade-off analysis.

10%

Midterm

Modules 1–4: systems foundations, LLM engineering, RAG and agents.

10%

Unit quizzes

Twenty-four short online quizzes, one per unit, with unlimited attempts.

Weightings are indicative and confirmed in the course syllabus.

  • Assignment 1 AI Solution Architecture — design an enterprise AI architecture Brief
  • Assignment 2 Retrieval-Augmented Generation System — build a complete RAG application Brief
  • Assignment 3 Agentic AI Application — build an agent with tool use and task execution Brief
  • Assignment 4 Multimodal AI Solution — integrate text and image processing Brief
  • Assignment 5 AI Operations Project — deploy and monitor an AI application Brief
  • Assignment 6 AI Governance Assessment — audit a complex AI system Brief

Capstone

Enterprise intelligent application

Design, build, deploy and evaluate a complete AI system. You choose one of four tracks and work through twelve structured development phases from proposal to final demonstration.

Choose your track

Track A

Intelligent Knowledge Assistant

Corporate assistant, policy assistant or research assistant grounded in a document corpus.

 Track B

Industry AI System

Healthcare advisor, financial analysis assistant or educational tutor for a specific domain.

 Track C

Multi-Agent System

Business process automation, research automation or workflow orchestration across agents.

 Track D

Multimodal Application

Vision-language assistant, document understanding system or media analysis platform.

What you submit

  • Project proposal and stakeholder analysis
  • Requirements and architecture documentation
  • Knowledge and data design
  • Working AI components and engineered workflows
  • Evaluation framework and test results
  • Governance review and deployment plan
  • Final demonstration and report

Portfolio ready

The capstone produces a deployed system with architecture documentation and an evaluation report — exactly the artefacts employers ask for in AI engineering roles.

Governance review is mandatory

No capstone is accepted without a completed governance review. A system that works but cannot be shown to be safe, fair and auditable does not pass.

  1. Project ProposalDefine the problem, the users and the value the system delivers.
  2. Stakeholder AnalysisIdentify everyone affected and what they need from the system.
  3. Requirements EngineeringTurn needs into testable functional and non-functional requirements.
  4. System ArchitectureDesign the components, interfaces and data flow end to end.
  5. Knowledge and Data DesignPlan the corpus, schemas, embeddings and retrieval strategy.
  6. AI Component DevelopmentBuild and integrate the models, retrievers and agents you need.
  7. Workflow EngineeringOrchestrate components into reliable, observable pipelines.
  8. Evaluation FrameworkDefine how the whole system will be measured before you build it.
  9. Governance ReviewAssess risk, fairness, privacy and compliance obligations.
  10. Deployment PlanningPlan infrastructure, cost, scaling and rollback.
  11. System TestingTest quality, robustness, safety and failure behaviour.
  12. Final DemonstrationPresent the deployed system and defend your engineering decisions.

Tools & technology

The AI engineering stack

The course uses the tooling you will meet in industry: orchestration frameworks, vector stores, containerisation and major cloud AI platforms.

Python 3 The language for the entire course.
LangChain / LlamaIndex Orchestration frameworks for RAG and agentic applications.
Vector databases Embedding storage and similarity search at scale.
Cloud AI platforms Azure AI, AWS AI and Google Cloud AI services.
Docker & CI/CD Packaging, deployment pipelines and version control.
Observability tooling Tracing, logging, evaluation and hallucination detection.

Questions

Frequently asked questions

Does COMP429 teach new machine learning algorithms?

No — deliberately so. COMP429 assumes the algorithmic knowledge from COMP329 and introduces no new learning theory. Its subject is how to engineer, integrate, deploy and govern systems built from models you already understand.

What exactly are the prerequisites?

COMP329 Advanced Machine Learning and Deep Learning, or equivalent. You should already be able to train and evaluate neural networks, work with pretrained transformers, and write well-structured Python. Some familiarity with cloud services and version control is helpful.

Do I need paid API keys or cloud accounts?

Teaching accounts and credits are provided for the cloud platforms used in the course. Where possible, labs are also designed to work with locally-hosted open models so that cost is never a barrier to learning.

How much of the course is coding versus design?

Roughly half and half. You will write substantial code, but a large proportion of the assessed work is architectural: requirements, diagrams, trade-off analyses, evaluation frameworks and governance documentation.

How much time should I expect to spend each week?

Plan for roughly 12–14 hours per week. Capstone work in particular tends to expand, so start early and keep the evaluation framework in view from the beginning.

Can I choose my own capstone problem?

Yes, provided it fits one of the four tracks and has a genuine user, a real dataset or corpus, and measurable success criteria. Projects proposed by industry partners are also welcome.

How does this prepare me for COMP529?

COMP529 is a research-oriented course. The systems thinking, evaluation discipline and governance awareness developed in COMP429 are the practical grounding you need before engaging critically with the research literature.

Ready to engineer intelligent systems?

Begin with Module 1, Unit 1 — what separates a model from a system, and why that distinction decides whether an AI project succeeds.

Start Unit 1 Download syllabus
👤