This foundational module introduces how traditional ML and DL paradigms are evolving through the infusion of real-world context-driven prompts, setting the stage for the program's context engineering approach.

This module builds the Python programming foundation essential for AI/ML work, covering core libraries for data manipulation and exploratory data analysis.

This module covers the mathematical foundations underpinning machine learning, including linear algebra, probability, and optimization techniques critical for model training and evaluation.

This module focuses on preparing data for machine learning through robust engineering practices including pipelines, hyperparameter tuning, and reproducible model evaluation workflows.

This module covers core supervised and unsupervised ML algorithms, integrating context engineering principles to build more grounded and business-relevant predictive models.

This module explores modern deep learning architectures from ANNs to Transformers, applying context engineering techniques across Computer Vision and NLP applications.

This module introduces the core concepts of generative AI, covering large language models, embeddings, diffusion models, and transfer learning as the basis for building modern GenAI applications.

This module provides hands-on experience with LLM frameworks and prompt engineering techniques, enabling learners to build and manage production-grade LLM pipelines using industry tools.

This module provides a comprehensive deep-dive into retrieval-augmented generation, covering context design, memory management, safety governance, and production-ready evaluation frameworks for LLM systems.

This module explores multimodal AI systems that bridge vision and language, covering state-of-the-art models and techniques for tasks requiring joint understanding of images and text.

This module covers the design and implementation of autonomous AI agents capable of memory, tool use, planning, and collaboration within multi-agent systems for complex real-world tasks.

This module covers scalable and privacy-preserving ML approaches including federated learning architectures, security vulnerabilities, adversarial attack defences, and contextual applications in distributed environments.

This module addresses the responsible deployment of AI systems, covering bias detection, explainability methods, regulatory compliance frameworks including GDPR and DPDP Act, and enterprise-grade AI audit and risk management practices.

This domain module applies AI techniques to healthcare challenges including disease prediction, medical image analysis, and generative AI-powered clinical assistance tools.

This domain module explores AI applications in retail and e-commerce, covering personalisation, customer retention, intelligent search, and generative AI for content creation.

This domain module applies computer vision and AI-driven analytics to manufacturing use cases including defect detection, process optimisation, supply chain forecasting, and real-time safety monitoring.

This module covers the full lifecycle of deploying and maintaining ML models in production, including containerisation, CI/CD pipelines, experiment tracking, and system monitoring.

This module addresses the operational challenges of running generative AI systems in production, covering prompt quality evaluation, content moderation, hallucination testing, and cost optimisation strategies.

This capstone design module focuses on architecting robust AI products and systems, covering LLM system design patterns, chaining strategies, fallback mechanisms, and scalable prompt management.