phone iconSpeak with our expert +14109366066

Delivered in collaboration with Great Learning

Learn more about the course

Get details on syllabus, projects, tools, and more

Name
Email
Mobile Number

By submitting this form, you consent to our Terms of Use & Privacy Policy and consent to be contacted via email, phone (including by AI-generated/pre-recorded voice calls), SMS, or WhatsApp.

Certificate Program in Artificial Intelligence and Agentic AI Engineering

Certificate Program in Artificial Intelligence and Agentic AI Engineering

Download Brochure
Apply Now

Application closes 30th Jul 2026

Why should you join this program?

  • List icon

    Hands on Agentic AI Curriculum for Tech Practitioners

    Apply AI to real-world engineering challenges supported by access to OpenAI API keys and Cloud Labs from Great Learning. Work on hands-on projects and case studies across real-world workflows.

  • List icon

    Learn from JHU, a Leading US Research University

    Ranked #7 National University, #14 Best Global University, #2 in Computer Information Technology, reflecting JHU's leadership in research and innovation. (2026 Rankings)

PROGRAM OUTCOMES

What will you learn to build and apply?

Design, deploy, and operate AI systems in real-world production environments.

  • Design and implement production AI/ML systems on cloud platforms using end-to-end MLOps pipelines

  • Scale and deploy Generative and Agentic AI solutions in production using cloud-native LLMOps workflows

  • Evaluate, monitor, and secure Agentic AI systems using observability frameworks and continuous tracking

  • Integrate responsible AI practices, governance, privacy, and security across the entire system lifecycle

Earn a certificate of completion from Johns Hopkins University

  • #7 National University Rankings

    #7 National University Rankings

    U.S. News & World Report, 2026

  • #2 Computer Information Technology

    #2 Computer Information Technology

    U.S. News & World Report, 2026

  • #10 Most Innovative Schools

    #10 Most Innovative Schools

    US News and World Report, 2026

  • #14 Best Global University

    #14 Best Global University

    U.S. News & World Report, 2026

  • #1 Biomedical Engineering Program

    #1 Biomedical Engineering Program

    US News and World Report, 2026

KEY PROGRAM HIGHLIGHTS

Why choose this program?

  • List icon

    Learn from Johns Hopkins University faculty

    Learn through recorded lectures and faculty-led masterclasses to apply AI across real-world clinical and operational settings.

  • List icon

    Interactive mentorship by industry experts

    Learn from AI experts through mentorship sessions focused on practical applications, implementation challenges, and industry best practices.

  • List icon

    Hands-on learning

    Build an industry-ready portfolio to showcase proficiency in leading AI-powered tools and technologies acquired through hands-on projects and real-world case studies.

  • List icon

    Practical Agentic AI curriculum

    Learn from a cutting-edge curriculum covering data management, model training and deployment, MLOps, monitoring, and LLMOps for production-grade AI applications

  • List icon

    Dedicated support

    Access a dedicated program support team throughout your learning journey, and Academic Learning Support, which includes discussion forums and peer groups

  • List icon

    Elite credentials

    Upon program completion, earn a globally recognized Certificate of Completion and 16 Continuing Education Units (CEUs) from Johns Hopkins University

Skills You Will Learn

CI/CD PIPELINES

Enterprise LLMOps

RETRIEVAL-AUGMENTED GENERATION (RAG)

Drift Detection & Monitoring

Agentic AI Orchestration

Production MLOps Pipelines

Advanced RAG Architecture

Adversarial Workflow Testing

Responsible AI Governance

Multi-Cloud AI Deployment

AI-Assisted Programming

Data Operationalization

Programmatic Prompt Patterns

CI/CD PIPELINES

Enterprise LLMOps

RETRIEVAL-AUGMENTED GENERATION (RAG)

Drift Detection & Monitoring

Agentic AI Orchestration

Production MLOps Pipelines

Advanced RAG Architecture

Adversarial Workflow Testing

Responsible AI Governance

Multi-Cloud AI Deployment

AI-Assisted Programming

Data Operationalization

Programmatic Prompt Patterns

view more

  • Overview
  • Learning Journey
  • Curriculum
  • Projects
  • Tools
  • Certificate
  • Faculty
  • Mentors
  • Career Support
  • Fees

Who is the program for?

Professionals with a foundation in AI, ready to transition from building models to production-grade AI systems

  • Software Development Engineers

    Who want to add AI, machine learning, Generative AI, and Agentic AI capabilities to production systems using modern MLOps and LLMOps practices

  • DevOps, Platform, and Site Reliability Engineers

    Who want to extend their expertise into model versioning, drift detection, observability, and AI system operations

  • Cloud Engineers and Architects

    With Azure or AWS experience who want to specialize in deploying, monitoring, scaling, and governing AI and Agentic AI systems in cloud environments.

  • Data and AI Professionals

    Who want to bridge the gap between model development and production deployment through end-to-end AI engineering

  • Technology Leaders and Architects

    Who want a hands-on understanding of how to develop, scale, secure, and govern AI and Agentic AI systems in real-world enterprise environments

How is the program learning experience?

Our pedagogy is designed to ensure a holistic learning experience

  • banner-image

    Learn from world-renowned faculty

    Learn critical concepts through live masterclasses and recorded video lectures by JHU faculty

  • banner-image

    Work on hands-on projects

    Work on projects to apply the concepts & tools learnt in the module

  • banner-image

    Engage with your mentors

    Clarify your doubts and gain practical skills during weekly live sessions with industry experts

  • banner-image

    Get personalized assistance

    Our dedicated program support team will assist you through your learning journey

What will you learn in the program?

The curriculum is designed by faculty from Johns Hopkins University and leading industry practitioners. It covers key concepts to build robust, responsible, and scalable AI solutions for real-world business challenges leveraging key tools and technologies like Python, LangChain, LangGraph, Azure OpenAI, and Amazon Bedrock Agents.

Pre-Work

This course focuses on foundational concepts and introduces learners to cloud computing concepts and the cloud ecosystem, guides them through setting up a cloud environment, and provides an overview of real-world use cases for Artificial Intelligence applications on the cloud.

Concepts Covered:

- Introduction to Cloud Computing - Understanding Cloud Ecosystem - Real-world Use Cases for AI on Cloud

Course 01: AI, Generative AI, and Agentic AI Foundations

This course builds the essential foundation in Artificial Intelligence, Machine Learning, and Generative Artificial Intelligence needed to engineer production Artificial Intelligence systems. It covers the Artificial Intelligence landscape, Python programming, Exploratory Data Analysis, core Machine Learning techniques, Large Language Models, Prompt Engineering, Retrieval-Augmented Generation, and an introduction to Agentic Artificial Intelligence.

Week 01: Artificial Intelligence, Generative AI, and Agentic AI Landscape

Concepts Covered: - Artificial Intelligence Evolution and Landscape - Generative AI and Agentic Artificial Intelligence - Artificial Intelligence Applications and Adoption Challenges

Week 02: AI-Assisted Python Programming

Concepts Covered: - AI-Assisted Programming Fundamentals - Mental Models for AI-Assisted Programming - AI Tools and Best Practices

Week 03: AI-Assisted Exploratory Data Analysis

Concepts Covered: - Data Exploration and Exploratory Data Analysis - Feature Engineering and Encoding - Regression Modeling and Evaluation

Week 04: AI-Assisted Machine Learning Workflows

Concepts Covered: - Loan Delinquency Prediction - Binary Classification Modeling - Risk Assessment Workflows

Week 05: Prompt Engineering Using Large Language Models

Concepts Covered: - Prompt Engineering Fundamentals and Core Elements - Common Prompting Design Patterns - LangChain for Prompt Engineering

Week 06: Retrieval-Augmented Generation-Based Large Language Model Workflows

Concepts Covered: - Retrieval-Augmented Generation Fundamentals and Motivation - BERT Compared with GPT and Retrieval-Augmented Generation - Retrieval-Augmented Generation Pipelines and RAG Assessment Suite

Week 07: Introduction to Agentic AI

Concepts Covered: - PEAS Agent Framework - Environment Classification Types - Four Core Agent Architectures - Retrieval-Augmented Generation and ReAct Loops

Week 08: Project Week | Health Insurance Approval Prediction

Industry: Healthcare Build a claim approval prediction system that combines machine learning on structured claim data with LLM-based extraction of diagnosis context from physician notes to support faster and more accurate claim adjudication. Skills You Will Learn: Python, Pandas, Exploratory Data Analysis, Feature Engineering, Classification Modeling, Evaluation Metrics, LLM APIs, Prompt Engineering Note: Projects listed are indicative and subject to change.

Course 02: AI Ops Foundations

This course builds on the foundational AI concepts introduced in the previous course and focuses on the operational aspects of AI and Machine Learning. It explores key AI operations (AIOps) concepts, methodologies, and frameworks, with an emphasis on operationalizing data, managing ML workflows, and understanding the model training, evaluation, and deployment lifecycle.

Week 09: Introduction to AI Ops and AI Engineering

Concepts Covered: - Overview of AI Concepts and Drivers - Introduction to AI Operations - AI Operations Frameworks and Challenges

Week 10: Operationalizing Data for AI

Concepts Covered: - Overview of AI Concepts and Drivers - Introduction to AI Operations - AI Operations Frameworks and Challenges

Week 11: Model Training and Evaluation

Concepts Covered: - Overview of Machine Learning Methodologies Including Supervised, Unsupervised, and Reinforcement Learning - Overview of Machine Learning Model Lifecycle - Model Training - Model Evaluation

Course 03: Production-Grade Deployment with MLOps

This course is dedicated to the practical implementation of MLOps. It covers the architecture and components of MLOps pipelines, including continuous integration and continuous delivery principles and different deployment strategies. Key topics include model monitoring, model degradation, drift detection, and ensuring version management and reproducibility in production environments.

Week 12: MLOps Fundamentals and Model Deployment

Concepts Covered: - Introduction to MLOps - Key Features of MLOps - Productionizing a Machine Learning Model - Model Deployment Including Types and Requirements

Week 13: Building MLOps Pipelines

Concepts Covered: - The Need for MLOps Pipelines - Continuous Integration and Continuous Deployment Pipeline Architecture and Components - Experimentation Tracking - Version Management and Reproducibility

Week 14: Monitoring and Performance Analysis in AI Systems

Concepts Covered: - Monitoring Including Resource Usage, Performance, Retraining Frequency, and Cost - Model Degradation - Drift Detection Including Data Drift, Concept Drift, Detection Techniques, and Interpretation

Week 15: Learning Break

Week 16: Project Week | Credit Default Risk Scoring

Industry: Finance Description: Build an automated MLOps pipeline that predicts borrower default risk from financial and behavioral data and supports scalable, production-ready lending workflows. Skills You Will Learn: Python, Pandas, Scikit-Learn, MLflow, Model Deployment, MLOps, CI/CD, Experimentation Tracking Note: Projects listed are indicative and subject to change.

Course 04: LLMOps and Responsible AI Usage

This course focuses on the operationalization and responsible use of Generative AI and Agentic AI. It introduces LLMOps fundamentals, implementing continuous integration and continuous delivery and monitoring for large language models, and the deployment of agentic AI systems. The critical component of evaluating and securing agentic AI systems and understanding responsible AI will also be covered.

Week 17: LLMOps Fundamentals

Concepts Covered: - Introduction to LLMOps - Differences Between LLMOps and Traditional MLOps - Data Management for LLMs (Sourcing, Cleaning, and Preprocessing) - Data Annotation, Versioning, and Management - Storing and Accessing Large Datasets

Week 18: LLMOps in Production

Concepts Covered: - Setting Up Continuous Integration and Continuous Delivery Pipelines for Large Language Models - Retraining and Automated Fine-Tuning - Monitoring Large Language Models in Production - Feedback Loops and Data Collection

Week 19: Agentic AI in Production

Concepts Covered: - Agentic AI Design Patterns and Orchestration - Tool Integration Patterns Including Application Programming Interfaces, Databases, and Retrieval-Augmented Generation - Memory and State Management - Observability in AI Agents Including Traces Across Steps and Tool Calls - Deploying Agentic AI Systems

Week 20: Evaluating and Securing Agentic AI Systems

Concepts Covered: - Agentic AI System Evaluation Including Task Success Rate, Tool-Call Accuracy, Groundedness, and Rubric-Based Human Evaluation - Testing Agentic AI Workflows Including Unit, Integration, and End-to-End Testing, Adversarial Testing, Prompt Injection, and Jailbreak Attempts - Tool Safety and Access Control - Data Protection - Safety and Policy Enforcement Including Guardrails, Refusal, and Escalation - Monitoring, Incident Response, Continuous Improvement, and Release Management

Week 21: Responsible AI and AI Ops Adoption

Concepts Covered: - Overview of Responsible AI - Adopting Responsible AI Including Objectives and Ethics - Risks and Complexities - Risk Management Process - AI Adoption Blueprint

Week 22: Project Week | Agentic AI-Powered Shopping Assistant

Industry: Retail Description: Develop a shopping assistant powered by Agentic AI that understands customer intent, retrieves relevant information, executes actions such as order tracking, and delivers personalized support through a production-ready LLMOps system. Skills You Will Learn: Python, Large Language Models, Prompt Engineering, LangChain, OpenAI APIs, LangGraph, Agentic AI Note: Projects listed are indicative and subject to change.

Self-Paced Module: Claude-Based AI Workflows

This module is designed to build practical capability in applying Generative AI and Agentic AI using the Claude ecosystem in real-world contexts. Participants build the ability to design, execute, and evaluate AI-driven workflows for real-world applications, supported by structured learning. *Disclaimer: Access to tools within the Claude ecosystem is not included as part of the program. Participants may choose to explore advanced capabilities independently.

Design and Execute AI Workflows

- Model selection and prompt engineering using Claude Chat - Agentic workflow design and orchestration using Claude CoWork - Plan → Approve → Execute → Iterate framework - Designing workflows with reasoning, tools, and multi-step execution - Applying concepts through real-world case studies

Build and Deploy AI Systems at Scale

- API integration and model usage using Claude Code - Tool integration using the Model Context Protocol - Designing agentic systems with memory, tools, and orchestration - Performance optimization, cost considerations, and system reliability - Responsible AI principles, including alignment approaches such as Constitutional AI

Please Note

- The curriculum is subject to periodic review and updates at the discretion of the faculty to ensure alignment with industry requirements. - Claude API access is not included as part of the program. Learners may explore advanced usage independently.

Note: The curriculum listed above are indicative and subject to updates as technology evolves.

What are the projects and case studies?

Apply AI to real-world challenges through hands-on projects and case studies

project icon

healthcare | sample project

HEALTH INSURANCE CLAIM APPROVAL PREDICTION

Description

Build a claim approval prediction system that combines machine learning on structured claim data with LLM-based extraction of diagnosis context from physician notes to support faster and more accurate claim adjudication.

Skills you will learn

  • Python
  • Pandas
  • Exploratory Data Analysis
  • Feature Engineering
  • Classification Modeling
  • Evaluation Metrics
  • LLM APIs
  • Prompt Engineering
project icon

finance | sample project

CREDIT DEFAULT RISK SCORING

Description

Build an automated MLOps pipeline that predicts borrower default risk from financial and behavioral data and supports scalable, production-ready lending workflows.

Skills you will learn

  • Python
  • Pandas
  • Scikit-Learn
  • MLflow
  • Model Deployment
  • MLOps
  • CI/CD
  • Experimentation Tracking
project icon

retail | sample project

AGENTIC AI-POWERED RETAIL SHOPPING ASSISTANT

Description

Develop a shopping assistant powered by Agentic AI that understands customer intent, retrieves relevant information, executes actions such as order tracking, and delivers personalized support through a production-ready LLMOps system.

Skills you will learn

  • Python
  • Large Language Models
  • Prompt Engineering
  • LangChain
  • OpenAI APIs
  • LangGraph
  • Agentic AI
project icon

Healthcare | sample Case Study

HOSPITAL READMISSION RISK PREDICTION SYSTEM

Description

Learn how production-oriented machine learning workflows can support healthcare teams by identifying patients at higher risk of readmission and enabling data-informed care decisions.

Skills you will learn

  • Model Deployment
  • MLOps Fundamentals
  • Monitoring
  • Production AI Workflows
project icon

Sales | sample Case Study

AI-POWERED SALESFORCE CRM Q&A ASSISTANT

Description

Learn how to build a Retrieval-Augmented Generation (RAG) assistant that ingests Salesforce CRM documents, stores embeddings in a Chroma vector database, retrieves relevant context using LangChain, and generates accurate, grounded responses with large language models. Evaluate the assistant using key LLM quality metrics, including groundedness, relevance, and faithfulness.

Skills you will learn

  • Retrieval-Augmented Generation (RAG)
  • LangChain Workflows
  • Chroma Vector Database
  • Prompt Engineering
  • LLM Evaluation
project icon

RETAIL | sample CASE STUDY

AI-ASSISTED CLOUD KITCHEN INVENTORY SIMULATION

Description

Learn how to apply AI-assisted coding, structured prompting, testing, and debugging techniques to develop workflows that manage inventory, process orders, track expiry, and support automated restocking decisions.

Skills you will learn

  • AI-Assisted Coding
  • Structured Prompting
  • Testing and Debugging
  • Workflow Automation
project icon

SALES | sample CASE STUDY

AI-ASSISTED EDA FOR SALES DRIVERS ANALYSIS

Description

Learn how to combine AI-assisted exploratory data analysis with regression modeling to identify factors that influence sales performance and support forecasting and planning decisions.

Skills you will learn

  • Exploratory Data Analysis
  • Feature Engineering
  • Regression Modeling
  • Business Insight Generation
project icon

Customer Analytics | sample CASE STUDY

AI-ASSISTED ML WORKFLOW FOR CUSTOMER CHURN PREDICTION

Description

Learn how to develop an end-to-end machine learning workflow, from data exploration and feature engineering to model evaluation and explainability, to support customer retention decisions.

Skills you will learn

  • Classification Modeling
  • Feature Engineering
  • Model Evaluation
  • Explainability

Note: The projects listed above are indicative and subject to updates to the curriculum.

Which tools will you learn and apply?

Work with a comprehensive suite of modern, industry-standard tools, techniques, and algorithms

  • tools-icon

    Python

  • tools-icon

    OpenAI APIs

  • tools-icon

    Scikit-Learn

  • tools-icon

    LangChain

  • tools-icon

    LangGraph

  • tools-icon

    ChatGPT

  • tools-icon

    Azure ML Studio

  • tools-icon

    ChromaDB

  • tools-icon

    FAISS

  • tools-icon

    Github

  • tools-icon

    ML Flow

  • tools-icon

    Streamlit

  • tools-icon

    Pandas

Note: The tools listed above are indicative and subject to updates as technology evolves.

Earn a Certificate of Completion from Johns Hopkins University

Stand out in a competitive market with a Certificate of Completion that validates the expertise developed through rigorous, practical assessments.

certificate image

* Image for illustration only. Certificate subject to change.

Who are the faculty for the program?

Learn from renowned JHU faculty and build expertise in AI agents, autonomous systems, and AI implementation

  • Dr. Ian McCulloh

    Dr. Ian McCulloh

    Manager of Artificial Intelligence Executive and Professional Education, Johns Hopkins University

    Served as Chief Data Science and MD of AI, Accenture Federal Services

    Author of three books and over 100 peer-reviewed papers

    Know More
    Company Logo
  • Kiran Chittargi

    Kiran Chittargi

    Adjunct Faculty - Computer Science, Johns Hopkins University

    Program Director at Microsoft

    Global Expansion Lead for Azure

    Know More
    Company Logo
  • Dr. Shelby Wilson

    Dr. Shelby Wilson

    Senior Data Scientist - The Johns Hopkins University Applied Physics Laboratory

    Expert in applied mathematics, computational epidemiology, and ML.

    Over a decade of experience solving real-world problems with mathematical and AI tools.

    Know More
    Company Logo
  • Dr. Pedro Rodriguez

    Dr. Pedro Rodriguez

    Faculty, Johns Hopkins University AI Program

    Oversees 250+ AI/ML researchers on projects for the Department of Defense, Intelligence Community, and other government agencies

    Brings 20+ years of expertise in AI/ML algorithms for detection, tracking, classification, and sensor fusion

    Know More
    Company Logo
  • Dr. William Gray-Roncal

    Dr. William Gray-Roncal

    Principal Research Scientist - Johns Hopkins University Applied Physics Laboratory

    Expert in data science, neuroscience, AI, and precision medicine.

    Leads cutting-edge research in brain network mapping and analysis.

    Know More
    Company Logo
  • Dr. Iain Cruickshank

    Dr. Iain Cruickshank

    Faculty Member, Johns Hopkins University

    ML expert applying AI to intelligence, cybersecurity, and social data

    Ph.D, Societal Computing, Carnegie Mellon University School of Computer Science

    Know More
    Company Logo

Who are the mentors for weekly live sessions?

Learn from seasoned AI industry mentors to apply concepts and build practical skills.

  • Hassan Ayman - Mentor

    Hassan Ayman linkin icon

    Senior Data Scientist, IBM
    Company Logo
  • Tina Kovacova - Mentor

    Tina Kovacova linkin icon

    Data Advisor, Kaggle
    Company Logo
  • Arooj Ahmed Qureshi - Mentor

    Arooj Ahmed Qureshi linkin icon

    Senior Manager AI Engineering, Bell
    Company Logo
  • Ishwor Bhusal - Mentor

    Ishwor Bhusal linkin icon

    Data Scientist - Supply Chain Data Innovation, Nissan Motor Corporation
    Company Logo

Note: The mentors listed above are indicative and subject to change based on availability and scheduling.

Dedicated Career Support

  • banner-image

    Resume Builder

    Get access to an AI-powered resume builder to create professional, impactful resumes aligned with targeted roles.

  • banner-image

    Mock Interviews

    Benefit from unlimited mock interviews powered by AI to practice and refine interview skills.

What are the fees for the program?

The course fee is USD 3,500

Advance your career

  • benifits-icon

    Learn to build, deploy, and operate AI and Agentic AI systems in real-world production environments

  • benifits-icon

    Add leading AI tools to an industry-ready portfolio to showcase skills and proficiency

  • benifits-icon

    Learn from AI experts in weekly live online sessions focused on real-world implementation

  • benifits-icon

    Receive a Certificate of Completion and 16 CEUs from Johns Hopkins University

project icon

Easy payment plans

Avail our EMI options & get financial assistance

  • discount available

    Scholarship: USD 3,500 USD 3,300

    One Time Discount: USD 3,500 USD 3,125

Third Party Credit Facilitators

Check out different payment options with third party credit facility providers

affirm splitit

*Subject to third party credit facility provider approval based on applicable regions & eligibility

Take the next step

timer
00 : 00 : 00

Apply to the program now or schedule a call with a program advisor

Scale smarter with AI

Application Closes: 30th Jul 2026

Apply Now

Application Closes: 30th Jul 2026

Talk to our advisor for program details

Schedule a call

Application Process

Admissions close once the requisite number of participants enroll. Apply now.

  • steps icon

    Fill application form

    Apply by filling out a simple online application form.

  • steps icon

    Review process

    A panel from Great Learning will review your application to determine your fit for the program.

  • steps icon

    Join program

    Receive an offer for a seat in the upcoming cohort of the program post a final review.

Participant Eligibility

  • This program is tailored for working professionals with a foundational knowledge of AI.

Limited seats available

Apply now scale smarter with AI

Apply Now

Delivered in Collaboration with:

Johns Hopkins University is collaborating with online education provider Great Learning to offer the Certificate Program in AI and Agentic AI Engineering. Great Learning is a professional learning company with a global footprint in 170+ countries. Its mission is to make professionals around the globe proficient and future-ready. This program leverages JHU's leadership in innovation, science, engineering, and technical disciplines developed over years of research, teaching, and practice. Great Learning manages the enrollments and provides industry experts, student counselors, course support and guidance to ensure students get hands-on training and live personalized mentorship on the application of concepts taught by the JHU faculty.

Certificate Program in Artificial Intelligence and Agentic AI Engineering

Download Brochure
Apply Now

phone icon Application Closes 30th Jul 2026

Got more questions? Talk to us

Connect with our advisors and get your queries resolved

Speak with our expert +14109366066 or email to ai-engineering.jhu@mygreatlearning.com

career guidance