ECS8060: AI Engineering
Queen's University Belfast
ECS8060
AI Engineering
Queen's University Belfast — Summer 2026

Schedule

This tentative schedule outlines all lectures, assignments, and deadlines across the three parts of the course: building intelligent systems with foundation models, adapting foundational models with post-training methods, and deploying them as production systems. Materials will be posted before each session on Canvas. The schedule is subject to change.

Books

The following books may be helpful resources for the course, but they are not required reading.

  • AI Engineering: Building Applications with Foundation Models by Chip Huyen.
  • Reinforcement Learning from Human FeedbackA short introduction to RLHF and post-training focused on language models by Nathan Lambert

    • Date Topic Readings
    Part 1: Building Intelligent Systems
    Jun 03 Lecture 1: Introduction, Foundational Models
    [slides] [notes]
    Readings Attention Is All You Need
    		 Attention Is All You Need
    Jun 03 Lecture 2: How to Build Foundational Models
    [slides] [notes]
    Jun 10 Lecture 3: Problem Framing, Evaluation, and Model Selection
    [slides] [notes]
    Readings Holistic Evaluation of Language Models
    		 Holistic Evaluation of Language Models
    Jun 10 Lecture 4: Prompting and In-Context Learning
    [slides] [notes]
    Readings Language Models are Few-Shot Learners
    		 Language Models are Few-Shot Learners
    Jun 17 Lecture 5: Context Engineering - Contextual Retrieval
    [slides] [notes]
    Readings Retrieval-Augmented Generation
    		 Retrieval-Augmented Generation
    Jun 17 Lecture 6: Advanced Topics in Retrieval
    [slides] [notes]
    Jun 24 Lecture 7: Multimodal Foundation Models
    [slides] [notes]
    Readings Learning Transferable Visual Models From Natural Language Supervision
    		 Learning Transferable Visual Models From Natural Language Supervision
    Jun 24 Guest Lecture - Multimodal by Dr. Hira
    Jul 01 Agentic AI Seminar with AMD
    Jul 08 Lecture 8: Agentic AI
    [slides] [notes]
    Jul 08 Lecture 9: Agentic AI
    [slides] [notes]
    Part 2: Adapting and Deploying Models
    Jul 15 Lecture 10: Why Fine-tune, Memory Math, Instruction Tuning
    [slides] [notes]
    Readings Training language models to follow instructions
    		 Training language models to follow instructions
    Jul 15 Lecture 11: Distillation, Parameter-Efficient Fine-Tuning
    [slides] [notes]
    Readings LoRA: Low-Rank Adaptation
    		 LoRA: Low-Rank Adaptation
    Jul 22 Lecture 12: Preference Optimisation, RLHF, Verifiable Rewards
    [slides] [notes]
    Readings Direct Preference Optimization
    		 Direct Preference Optimization
    Jul 22 Lecture 13: Data Curation and Synthetic Data for Fine-tuning
    [slides] [notes]
    Jul 29 Lecture 14: Inference Optimisation
    [slides] [notes]
    Readings Efficient Memory Management for LLM Serving with PagedAttention
    		 Efficient Memory Management for LLM Serving with PagedAttention
    Jul 29 Lecture 15: Building Model APIs
    [slides] [notes]
    Aug 05 Lecture 16: Building Backend Systems
    [slides] [notes]
    Aug 05 Lecture 17: Observability and Feedback
    [slides] [notes]
    Aug 12 Guest Lecture - AI Safety by Dr. Ahmed