• Inactive for Year: 2026/27

• Module Leader(s): Professor Raj Ranjan
• Lecturer: Dr Ellis Solaiman, Dr Deepayan Bhowmik, Dr Dev Jha

• Owning School: Computing
• Teaching Location: Newcastle City Campus

Semesters

Your programme is made up of credits, the total differs on programme to programme.

Aims

This module develops your understanding of how modern artificial intelligence systems are deployed, managed, and evaluated within practical computational environments. You will study AI deployment workflows, including infrastructure selection, data pipelines, GPU and cloud computing, model serving, orchestration, monitoring, and scalable deployment architectures. The emphasis is on designing reliable, efficient, and responsible AI systems while evaluating performance, scalability, sustainability, and operational constraints within real-world applications.

Outline Of Syllabus

Topics covered by this module include:


Introduction to AI deployment, including the transition from trained models to production AI systems, services, and applications
Cloud and data-centre architectures, including compute, storage, networking, virtualisation, containers, and orchestration
Data flow design for AI systems, including data ingestion, preprocessing, feature pipelines, inference workflows, and feedback loops
Model serving approaches, including REST APIs, batch and streaming inference, serverless deployment, and edge-cloud systems
AI hardware and accelerated computing, including GPUs, TPUs, memory management, parallelism, batching, and hardware-aware design
Scalable AI pipelines, including workflow orchestration, dependency management, scheduling, reproducibility, and fault tolerance
AI agents and deployment architectures, including tool use, retrieval-augmented generation systems, multi-agent workflows, and safety boundaries
Monitoring and observability for AI systems, including logging, metrics, tracing, drift detection, failure analysis, and performance monitoring
Benchmarking and evaluation of AI pipelines, including measures of accuracy, latency, throughput, scalability, robustness, fairness, cost, and energy use

Teaching Methods

Teaching Activities

Teaching Rationale And Relationship

Preparation and completion of summative report

Assessment Methods

The format of resits will be determined by the Board of Examiners

Exams

Other Assessment

Formative Assessments

Formative Assessment is an assessment which develops your skills in being assessed, allows for you to receive feedback, and prepares you for being assessed. However, it does not count to your final mark.

Assessment Rationale And Relationship

The digital examination assesses students’ understanding of the principles, architectures, and operational considerations associated with modern AI deployment systems within a controlled environment. The examination evaluates students’ ability to reason about AI pipelines, deployment workflows, scalability, monitoring, infrastructure choices, and responsible practice, with an emphasis on conceptual understanding, evaluation of system performance, and applied technical decision making. The examination primarily assesses students’ ability to analyse deployment architectures, operational constraints, and responsible AI deployment practices. (MLO2, MLO3, MLO4)

The report provides students with the opportunity to apply knowledge and techniques from the module within an applied AI systems context. Students will analyse, evaluate, and communicate aspects of AI deployment, performance, infrastructure, or operational design through a structured technical report supported by appropriate figures and discussion. The report particularly emphasises the development and implementation of AI-based solutions within realistic deployment contexts, alongside the evaluation and communication of engineering and operational decisions. (MLO1, MLO4)

The formative assessment provides students with an opportunity to practise technical analysis and written communication in advance of the summative report assessment and receive feedback on the presentation and evaluation of AI systems concepts.

The assessment structure supports the development of both conceptual understanding and applied systems thinking, enabling students to evaluate, communicate, and reason about the deployment and operation of modern AI systems within realistic computational environments.

Alternative assessment:

For students with a Student Support Plan (SSP) who have alternative assessment as a reasonable adjustment and/or students with supported Personal Extenuating Circumstances (PEC), it may be necessary to set an alternative assessment as presented below. Due to the professional requirements of some programmes, alternative assessments may not be available even where students are eligible.

A 24-hour open-book assessment may be offered as an alternative to the digital examination where appropriate.

Reading Lists

• DSC2005's Reading List

Timetable

• Timetable Website: www.ncl.ac.uk/timetable/
• DSC2005's Timetable