Johns Hopkins AI and Agentic AI Engineering Program
- The 22-week online program focuses on building, deploying, and operating AI and Agentic AI systems across cloud environments and real-world production settings.
- Participants will learn through recorded lectures, live masterclasses by Johns Hopkins University faculty, weekly mentorship sessions with industry experts, case studies, and hands-on projects.
- The curriculum covers AI, Generative AI, and Agentic AI foundations, AI Ops, MLOps, LLMOps, Agentic AI deployment, monitoring, security, and Responsible AI.
- Successful participants will receive a Certificate of Completion and 16 Continuing Education Units from Johns Hopkins University.
Johns Hopkins University has launched its Certificate Program in Artificial Intelligence and Agentic AI Engineering, a 22-week online program designed for software developers, data and AI professionals, DevOps and platform engineers, cloud architects, and technology leaders with prior programming experience who want to build, deploy, and operate AI systems.
The program addresses a growing challenge in enterprise AI adoption. While building AI prototypes has become increasingly accessible, operationalizing these systems requires expertise in deployment, monitoring, security, governance, and ongoing AI operations.
Why Is Production-Ready AI Engineering Important for Agentic AI?
More than 40% of Agentic AI projects are expected to be canceled by the end of 2027, according to Gartner, citing escalating costs, unclear business value, and inadequate risk controls. This underscores why organizations need more than AI prototypes; they need systems that can be deployed, monitored, secured, and governed in production.
Production-ready AI requires capabilities across MLOps, LLMOps, deployment, observability, evaluation, security, and Responsible AI. The Johns Hopkins University program addresses these areas through its curriculum on production deployment, Agentic AI operations, system evaluation, and AI governance.
Why Production-Ready AI Skills Matter Now
Demand for AI engineering talent continues to grow as organizations add AI systems to products and business processes. LinkedIn’s September 2025 AI Labor Market Update reported that hiring of AI engineering talent grew by more than 25% year over year in 2025. The increase signals demand for professionals who build and deploy AI systems.
Scaling those systems presents a separate challenge. IBM’s 2025 CEO Study found only 16% of AI initiatives had scaled across the enterprise. Together, the findings point to expanding AI work and uneven enterprise execution.
Curriculum and Learning Outcomes
The 22-week curriculum progresses from AI and Generative AI foundations to production-grade AI engineering, covering four courses:
- AI, Generative AI, and Agentic AI Foundations
- AI Ops Foundations
- Production-Grade Deployment with MLOps
- LLMOps and Responsible AI Usage
Participants begin with Python, EDA, and Machine Learning workflows during Weeks 1–4 before moving to advanced LLM prompting, RAG, and Agentic AI in Weeks 5–7.
The program then focuses on MLOps and production deployment, covering CI/CD, experimentation tracking, version management, monitoring, and drift detection. The final course addresses LLMOps, Agentic AI deployment, observability, security, and Responsible AI.
By completion, participants develop capabilities to deploy, monitor, secure, and govern AI and Agentic AI systems across their lifecycle, including cloud-based production environments.
From AI Development to Agentic AI in Production
A key component of the program is its focus on designing and operationalizing Agentic AI systems beyond experimentation.
Participants examine Agentic AI design patterns and orchestration, tool integration through APIs, databases, and RAG, memory and state management, and observability across agent steps and tool calls.
The curriculum also addresses the evaluation and security of Agentic AI systems. Participants study task success rates, tool-call accuracy, groundedness, human evaluation, adversarial testing, prompt injection, jailbreak attempts, access control, data protection, guardrails, escalation, incident response, and release management.
This is complemented by Responsible AI and AI Ops adoption, covering AI risks, ethics, risk management, and an AI adoption blueprint.
Hands-On Projects and Engineering Case Studies
The program includes 3 hands-on projects and 22+ case studies, giving participants opportunities to apply AI and Agentic AI concepts across different industries and technical workflows.
Indicative projects include:
- Health Insurance Claim Approval Prediction: Combines Machine Learning with LLM-based extraction of diagnosis information from physician notes.
- Credit Default Risk Scoring: Uses an automated MLOps pipeline to support scalable lending workflows.
- Agentic AI-Powered Retail Shopping Assistant: Uses Agentic AI to understand customer intent, retrieve information, and execute actions such as order tracking.
Case studies extend across healthcare, retail, sales, customer analytics, and other business settings. These include a hospital readmission risk prediction system, an AI-powered Salesforce CRM Q&A assistant using RAG and Chroma, an AI-assisted cloud kitchen inventory simulation, sales-driver analysis, and an AI-assisted customer churn workflow.
Across these projects and case studies, participants work with Python, Pandas, Scikit-Learn, MLflow, LangChain, LangGraph, OpenAI APIs, MLOps, LLMOps, and Agentic AI.
Program Delivery and Learning Experience
The program runs for 22 weeks, with an estimated commitment of 8–10 hours per week.
Learning combines recorded video lectures, monthly live masterclasses led by Johns Hopkins University faculty, and 18 live mentorship sessions with industry experts. Participants also receive access to project discussion forums, peer groups, academic support, and a dedicated program support team.
The program also includes access to OpenAI API keys and Cloud Labs from Great Learning for hands-on learning. An industry-ready e-portfolio allows participants to document their project work and demonstrate proficiency with the tools and technologies covered in the curriculum.
In addition, participants can explore a self-paced Claude-Based AI Workflows module covering model selection, Prompt Engineering, agentic workflow design, orchestration, tool integration, the Model Context Protocol, system reliability, cost considerations, and Responsible AI principles.
The program materials clarify that access to Claude APIs is not included as part of the program, and participants may explore advanced Claude capabilities independently.
Faculty and Industry Expertise
The program is delivered by Johns Hopkins University faculty and industry experts with experience across Artificial Intelligence, AI engineering, data science, cloud technologies, and Agentic AI.
Faculty featured in the program include Dr. Ian McCulloh, Manager of Artificial Intelligence Executive and Professional Education at Johns Hopkins University; Kiran Chittargi, Adjunct Faculty in Computer Science at Johns Hopkins University and Program Director at Microsoft; Dr. Shelby Wilson, Senior Data Scientist at the Johns Hopkins University Applied Physics Laboratory; Dr. Pedro Rodriguez, faculty in the Johns Hopkins University Artificial Intelligence program; Dr. Iain Cruickshank, faculty in Computer Science; and Dr. William Gray-Roncal, Principal Research Scientist at the Johns Hopkins University Applied Physics Laboratory.
Weekly mentorship is provided by industry professionals, with the brochure listing experts including Hassan Ayman, Senior Data Scientist at IBM; Tina Kovacova, Data Advisor at Kaggle; Arooj Ahmed Qureshi, Senior Manager AI Engineering at Bell; and Ishwor Bhusal, Data Scientist – Supply Chain Data Innovation at Nissan Motor Corporation.
Who Is the Program For?
The program is designed for technology professionals with programming experience who want to develop the skills needed to build, deploy, and operate AI systems in production environments.
The intended audience includes:
- Software Development Engineers looking to add AI, Machine Learning, Generative AI, and Agentic AI capabilities to production applications.
- DevOps, Platform, and Site Reliability Engineers seeking to extend their expertise into model versioning, observability, drift detection, and AI operations.
- Cloud Engineers and Architects with Azure or AWS experience who want to work on deploying, monitoring, scaling, and governing AI systems.
- Data and AI Professionals looking to bridge the gap between model development and production deployment.
- Technology Leaders and Architects who oversee AI initiatives and need a structured understanding of developing, scaling, securing, and governing AI systems in enterprise environments.
Certificate and Program Recognition
Participants who successfully complete the program receive a Certificate of Completion and 16 Continuing Education Units (CEUs) from Johns Hopkins University. The brochure states that the 16 CEUs represent 160 learning hours.
The program also provides an opportunity to build an e-portfolio documenting hands-on projects, applied skills, and experience with selected AI tools and technologies.
About Johns Hopkins University
Johns Hopkins University brings together research and academic expertise across Artificial Intelligence, Machine Learning, Deep Learning, Generative AI, engineering, and related disciplines. The program draws on this interdisciplinary foundation to examine the development and operation of AI systems in real-world environments.
About Great Learning
Great Learning is the program partner supporting delivery of the Certificate Program in Artificial Intelligence and Agentic AI Engineering. The company offers professional and higher education programs across technology, data, and business domains in collaboration with academic institutions, including Johns Hopkins University.
