Graduate Certificate in Generative AI & Prompt Engineering
Summary
This certificate prepares students to design, build, and evaluate modern generative-AI
solutions.
Using competencies from the courses Python for Data Science, Machine Learning Fundamentals, Digging Deep into Deep Learning, and Real-World Applications for Data Science and AI, learners gain practical skills in neural-network architecture, transformer models, and applied prompt-engineering workflows.
Location
Online
Completion Length
Length / Units: 6 weeks · 3 semester credits
(≈ 135 total hours)
Course Instructor
TBC
Program Description
This certificate prepares students to design, build, and evaluate modern generative-AI solutions for real-world professional environments.
Using competencies developed in the courses Python for Data Science, Machine Learning Fundamentals, Digging Deep into Deep Learning, and Real-World Applications for Data Science and AI, learners gain structured, hands-on experience in:
• Neural network architecture and training methodologies
• Transformer-based language and generative models
• Applied prompt-engineering workflows
• Model evaluation, optimisation, and deployment fundamentals
Graduates develop the technical proficiency required to design intelligent automation systems, develop generative-AI tools, and implement data-driven solutions across business, financial, and technological domains.
This program emphasises practical implementation, analytical rigour, and applied problem-solving to ensure graduates are prepared for modern AI-driven professional environments.
Program Learning Outcomes
Upon completion, students will be able to:
1. Apply Python programming, data structures, and visualization libraries to AI
workflows (CS1001 Python for Data Science).
2. Implement supervised and unsupervised machine-learning algorithms and evaluate
model performance (CS1006 Machine Learning Fundamentals).
3. Build and tune deep-learning architectures such as CNN and RNN, applying
TensorFlow and Keras frameworks (CS1007 Digging Deep into Deep Learning).
4. Utilize prompt-engineering strategies and transformer models for natural-language
and generative tasks (CS1009 Real-World Applications for Data Science and AI).
5. Integrate responsible-AI and ethical guidelines into generative-model design.
Course Content (6-Week Outline)
01
Python Foundations for Data Science and AI
CS1001 Python for Data Science
02
Machine-Learning Concepts and Evaluation
Methods
CS1006 Machine Learning
Fundamentals
03
Deep-Learning Networks (CNN / RNN) and
Transfer Learning
CS1007 Digging Deep into Deep
Learning
04
Generative and Transformer Models with
Prompt Engineering
CS1009 Real World Applications for
Data Science and AI
05
Project Sprint 1: Design and fine-tune a
prompt-driven model
Capstone Integration
06
Project Sprint 2: Prototype deployment and
ethical evaluation
Capstone Integration