AI for Software Developers (COMP 377)

An advanced technical elective that equips software engineering students with the skills to integrate modern artificial intelligence techniques into real-world software systems.

Course Description

COMP 377 introduces software developers to the principles and practice of artificial intelligence, with a strong emphasis on practical application. Beginning with foundational concepts in machine learning and supporting mathematics, students progress to building and deploying AI-enabled software systems.

The course covers neural networks, deep learning architectures, transformers, large language models (LLMs), and agentic retrieval-augmented generation (RAG). Learners gain hands-on experience with industry tools such as TensorFlow, LangChain, and LangGraph, and use AI-assisted development tools, including GitHub Copilot, to accelerate implementation workflows.

Topics also include cloud deployment, local model inference, and ethical considerations in AI-driven systems, preparing students for professional roles in AI-enhanced software development.

Course Learning Outcomes

Upon successful completion of this course, students will be able to:

Differentiate major subfields of artificial intelligence and analyze their applications in modern software development.
Compare types of learning in AI and examine the machine learning lifecycle through practical software-based examples.
Apply fundamental mathematical concepts, including linear algebra, probability, and calculus, to machine learning problems.
Implement and evaluate multilayer perceptron (MLP) and convolutional neural network (CNN) architectures for classification and prediction tasks.
Integrate advanced deep learning models, including transformers and large language models, into applications for complex classification and generation tasks.
Build generative AI applications using LLMs for dynamic user interaction, content creation, and language-based assistance.
Design and implement agentic AI systems that support autonomous decision-making and automation workflows.
Construct AI-powered agents capable of multi-step reasoning and tool use within full-stack software applications.
Assess ethical implications of AI systems and propose strategies to mitigate bias and unintended consequences.

Further Learning – AI Frameworks and Platforms

The following frameworks, platforms, and research resources support continued learning and experimentation in modern artificial intelligence.

TensorFlow – Open-source machine learning framework for research and production systems.
DeepLearning.AI – Courses and learning resources led by AI researchers.
OpenAI Research – Research advancing large-scale generative models.
LangChain – Tools supporting the development of AI-powered applications and agents.
LangGraph – Framework for building structured, controllable agentic AI systems.

Course Materials

Reference Textbooks

Bonnin, R. Machine Learning for Developers. Packt Publishing, 2017.
Goodfellow, I., Bengio, Y., Courville, A. Deep Learning. MIT Press, 2016 – Read online
Cai, S., Bileschi, S., Nielsen, E. D., Chollet, F. Deep Learning with JavaScript. Manning Publications, 2020.
Alammar, J., Grootendorst, M. Hands-On Large Language Models. O’Reilly Media, 2024.
Rothman, D. Transformers for Natural Language Processing and Computer Vision (3rd ed.). Packt Publishing, 2024.
Oshin, M., Campos, N. Learning LangChain. O’Reilly Media, 2025.

Supplementary Learning Resources

New Developments in Artificial Intelligence

The Batch (DeepLearning.AI) – Weekly updates on cutting-edge AI research, tools, and industry trends.
OpenAI Research – Frontier research on large language models, multimodal AI, and agentic systems.
Google DeepMind Research – Advances in foundation models, reasoning, planning, and scientific AI.
Anthropic Research – Research on safe, interpretable, and controllable large language models.
Hugging Face Research & Blog – Open-source model releases, benchmarks, and modern AI tooling.
Stanford Human-Centered AI (HAI) – Research on AI impact, evaluation, and governance.
arXiv – AI & Machine Learning – Latest preprints on emerging AI methods and architectures.