Applied AI Engineer Bootcamp
Learn AI from the ground up, build RAG applications and multi-agent systems, and deploy, monitor, and govern them in production.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
AI models are becoming more powerful and accessible, but building systems that hold up in production, with real users, high stakes, and close scrutiny, remains a rare and valuable skill. The bottleneck is no longer the models but the engineers who can take them into production.
The Applied AI Engineer Bootcamp takes you from the basics of programming and AI to building solutions companies can actually use. Through hands-on learning, you’ll work with machine learning, generative AI, RAG applications, and autonomous agents. You’ll learn how to turn an idea into a working AI product and prepare it for real-world use, not just experiment with prompts.
Designed for learners from both non-tech and tech backgrounds, the program supports career starters, professionals transitioning into technology, and those looking to add AI capabilities to their current roles. You’ll complete 10+ projects using 35+ industry tools, build a portfolio that demonstrates what you can deliver, and receive 1:1 coaching and interview preparation to support your job search.
Upon successfully completing the bootcamp, you’ll earn a certificate from Columbia Engineering Executive Education and Fullstack Academy, demonstrating your ability to build real-world AI solutions.
Course Prerequisites
This bootcamp is designed for professionals from diverse backgrounds. To help non-coders build a strong foundation and start on an equal footing, we include a Basics of Programming module, which we encourage learners to complete before starting the bootcamp.
Learners will need:
- Basic knowledge of math and statistics
- An eagerness to learn AI concepts and programming skills
- Prior work experience is welcome but not required
What You Will Learn
By the end of this program, learners will be able to:
- Master AI Engineering Foundations: Use Python, APIs, and data pipelines to build the groundwork every AI system depends on
- Develop GenAI and RAG Apps: Use LLMs, prompt engineering, and RAG to build AI applications grounded in relevant data
- Engineer Production-Ready Agents: Build, orchestrate, secure, and deploy autonomous agents that can use tools and complete complex tasks
Curriculum
- Module 1: Basics of Programming Concepts
- Understand computers, from transistors and binary to logic gates and memory
- Learn how code runs through compilers, interpreters, and the CPU
- Build programming logic with Scratch using variables, loops, and conditionals
- Module 2: Python Basics for Agentic AI and AI/ML
- Write Python code using syntax, variables, and core programming logic
- Configure your development environment and use everyday coding tools
- Build the foundation for AI, automation, and data-driven applications
- Module 3: Foundations of AI and Agentic AI
- Understand how AI systems are structured and what makes them intelligent
- Differentiate AI, machine learning, deep learning, GenAI, and Agentic AI
- Explore transformers, LLMs, and how AI agents work
- Module 4: Technical Foundations of Generative AI
- Understand how neural networks and deep learning work
- Trace the evolution from RNNs and LSTMs to transformers
- Build skills with TensorFlow, Keras, and Google Colab
- Module 5: Generative AI Applications, Context-Driven RAG, and Multimodal AI
- Explore prompt engineering and Retrieval-Augmented Generation
- Work with LangChain, multimodal AI, image generation, and fine-tuning
- Connect language models to company data
- Module 6: Agent Engineering, Multi-Agent Systems, and Workflow Automation
- Design agents using agentic RAG and memory strategies
- Explore multi-agent collaboration and orchestration patterns
- Create chatbots, agent teams, and automated workflows
- Module 7: Model Context Protocols and AI Tooling Frameworks
- Understand MCP, context management, and tool connections
- Design system prompts, persist context, and secure tool access
- Build and manage context-aware agents
- Module 8: LLM Operations and Deployment
- Deploy, monitor, and maintain LLM applications
- Evaluate models and apply responsible AI practices
- Keep live AI systems scalable and reliable
- Module 9: Building Customized LLMs With OpenAI
- Build RAG systems using vector search and knowledge graphs
- Adapt models using Hugging Face and LLaMA 2
- Deploy customized generative AI models in web applications
- Module 10: Shipping AI Products: Deployment, Operations, and Governance
- Compare deployment strategies, hosting models, and production setups
- Set up observability, monitoring, governance, and feedback systems
- Address bias, privacy, security, and legal risks
- Module 11: Capstone
- Apply the skills learned throughout the bootcamp
- Solve industry-specific challenges using GenAI and Agentic AI
- Showcase your knowledge and skills to employers
Instructors
George received a Ph.D. from the University of Chicago. An AI and data science leader, he has delivered applied machine learning solutions across subject domains, building scalable predictive models and data pipelines that support evidence-based decision-making. His work bridges academic research and industry application, with expertise in statistical analysis, bioinformatics, and molecular modeling. He also brings experience in graduate and undergraduate teaching and curriculum development.
Cristopher received an M.S. in Analytics from the Georgia Institute of Technology and an A.B. in Economics and Political Science from Harvard University. A published, award-winning data scientist, he currently builds machine learning models at CDLLife to inform recruitment and retention strategy. He previously led a 20+ person data science and engineering team at DataPoint Armenia, contributed to research at Harvard Business School, and founded Insider Advantage College Counseling.
Abishek received an M.S. in Computer Science from the Georgia Institute of Technology and a B.S. in Mathematics from The Ohio State University. He builds production-grade AI/ML systems, architecting end-to-end pipelines and predictive models that turn complex data into business decisions. He has delivered scalable healthcare and enterprise solutions at Acentra Health and Limbik, and previously drove AI integration and data-driven product work at Amazon, Mpathic, and Big Health.
David received a bachelor's degree from California State Polytechnic University, Pomona. He is an analytics and machine learning leader who designs data-driven transformations and builds predictive models and statistical methods that improve forecasting accuracy and operational efficiency. He has extensive experience architecting data pipelines and infrastructure for scalable analytics across industries, and he leads and mentors interdisciplinary teams, aligning analytics strategy with organizational goals.