Currently Empty: $0.00
Artificial Intelligence (AI) – AI Engineering Capstone
Capstone Advanced AI Engineering, Deployment, MLOps, AI Agents & Autonomous Systems
Target Audience – High School Students (Grades 9–12) and learners who have completed AI Specialist or have strong knowledge of Python, Machine Learning, Deep Learning, Generative AI, LLMs, Computer Vision, NLP, and AI development.
Program Pathway – AI Engineering Capstone
Total Duration –108 Hours
Delivery – Cohort-Based + Instructor-Led + Hands-On Labs
Program Goal
The AI Engineering Capstone program builds on the AI Specialist pathway and focuses on
designing, developing, integrating, testing, deploying, and documenting complete AI-powered systems. Students explore AI system architecture, advanced AI application development, model deployment, APIs, cloud AI, MLOps, Edge AI, advanced AI agents, robotics, autonomous AI, and end-to-end AI engineering projects.
Hands-On Learning Students learn through instructor-led lessons, advanced Python exercises, AI architecture activities, API development, LLM application development, RAG and AI agent labs, cloud deployment activities, MLOps exercises, Edge AI activities, robotics simulations, system integration exercises, testing and evaluation activities, mini-projects, assessments, and a final AI Engineering Capstone project.
What Students Build
Students develop practical experience with AI system architecture, AI-powered applications,
LLM applications, RAG systems, AI assistants, advanced AI agents, AI APIs, vector database
applications, cloud-deployed AI applications, model deployment workflows, MLOps pipelines, Edge AI applications, computer vision systems, robotics applications, autonomous AI workflows, and complete end-to-end AI engineering solutions.
Recommended Lab Requirements
Each student should ideally have:
Windows or Mac desktop/laptop
8 GB RAM minimum
16 GB RAM recommended
10 GB+ free storage
Windows/Mac systems are recommended. Chromebooks are not preferred. Cloud-based environments may be used for intensive AI model training, deployment, MLOps, and development activities, so a dedicated GPU is not required.
Next Step
Students who complete the AI Engineering Capstone will have experience designing and
developing end-to-end AI systems and can progress toward advanced studies and career
pathways in AI Engineering, Machine Learning Engineering, Generative AI Engineering,
MLOps, Cloud AI.
| Program Structure | ||
| Module | Topic | Hours |
| Module 1 | AI Engineering & System Architecture | 22 |
| Module 2 | Advanced AI Application Development & AI Agents | 22 |
| Module 3 | Model Deployment, Cloud AI & MLOps | 22 |
| Module 4 | Edge AI, Robotics & Autonomous AI Systems | 20 |
| Module 5 | AI Engineering Capstone Project | 22 |
| Total | 108Hours | |
Curriculum
- 5 Sections
- 0 Lessons
- 108 Hours
Expand all sectionsCollapse all sections
- Module 1 – AI Engineering & System Architecture0 Items✅ Topics :- AI Engineering Fundamentals, AI System Lifecycle, AI Solution Architecture, AI System Components, Data Pipelines, Model Selection, Model Integration, AI APIs, Application Layers, Backend & Frontend Concepts, AI Infrastructure Fundamentals, Databases for AI Applications, Vector Databases Fundamentals, Embeddings, Model Serving Fundamentals, System Integration, AI Workflow Design, Scalability Fundamentals, Performance Considerations, AI System Security, Responsible AI Architecture.
- Module 2 – Advanced AI Application Development & AI Agents0 Items✅ Topics :- Advanced Generative AI, Large Language Model Applications, Advanced Prompt Engineering, Structured Outputs, Function Calling, Tool Use, AI APIs, Multimodal AI Applications, Retrieval-Augmented Generation, Vector Search, Document Processing, Knowledge Bases, AI Assistants, Advanced AI Agents, Agent Workflows, Multi-Step Reasoning Workflows, Agent Tools, Agent Memory Fundamentals, Multi-Agent Systems Fundamentals, AI Application Integration, AI Evaluation, Hallucination Reduction, AI Safety & Guardrails.
- Module 3 – Model Deployment, Cloud AI & MLOps0 Items✅ Topics :- AI Model Deployment Fundamentals, Model Serving, REST APIs, API Development, Cloud AI Fundamentals, Cloud Compute, Cloud Storage, Containers & Docker Fundamentals, Deployment Workflows, Model Versioning, Data Versioning, MLOps Fundamentals, Continuous Integration & Continuous Deployment, Model Monitoring, Performance Monitoring, Model ,Evaluation in Production, Logging & Observability, Model Optimization, Scaling AI Applications, Cloud AI Services, AI Security, Cost Optimization, Production AI Lifecycle.
- Module 4 – Edge AI, Robotics & Autonomous AI Systems0 Items✅ Topics :- Edge AI Fundamentals, AI on Edge Devices, Edge Model Deployment, Model Optimization,Computer Vision on Edge Devices, Sensor Data Processing, Real-Time AI, Robotics AI Architecture, Robot Perception, Sensor Fusion, AI-Based Decision-Making, Path Planning, Navigation, Obstacle Detection & Avoidance, Autonomous Systems, Autonomous AI Workflows, Robotics Simulation, AI-Based Control, Human-Robot Interaction, Autonomous Vehicles & Drones, Edge AI Security, Robotics Safety.
- Module 5 – AI Engineering Capstone Project0 Items✅ Topics :- Problem Identification, Requirements Analysis, AI Solution Architecture, System Design, Data Selection & Preparation, Model Selection, AI Model Integration, LLM Integration, Generative AI Integration, RAG Integration, AI Agent Integration, API Development, Database or Vector Database Integration, Cloud Deployment, MLOps Concepts, Testing & Debugging, Performance Evaluation, Security Review, Responsible AI Review, Documentation, Deployment Planning, Project Demonstration, Final Presentation. Final Project: Build, deploy, test, and present an end-to-end AI engineering solution that integrates multiple AI technologies such as Machine Learning, Deep Learning, Generative AI, LLMs, RAG, AI Agents, APIs, Cloud AI, MLOps, Computer Vision, Edge AI, Robotics, or Autonomous AI.
