Building Customized LLMs with OpenAI
Develop advanced skills in customizing and deploying large language models via hands-on projects, covering RAG, fine-tuning, and applications.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
As generative AI transforms industries, professionals must not only understand how large language models (LLMs) work but also learn to customize and deploy them effectively. Off-the-shelf solutions rarely meet nuanced, context-specific needs. This program equips technical practitioners to build tailored AI systems that align with organizational goals, leverage proprietary data, and address industry-specific requirements.
Learners will gain hands-on experience implementing LLMs, focusing on advanced techniques such as retrieval-augmented generation (RAG) and fine-tuning. They will practice integrating AI APIs into real workflows, adapting models for domain-specific tasks, and building production-ready AI solutions through project-based learning and case studies.
Designed for intermediate to advanced learners with prior programming and AI fundamentals, this course is ideal for those who want to:
- Deepen practical skills in LLM implementation (software engineers and data scientists).
- Move beyond prompt engineering to develop customized, efficient models (AI/ML practitioners).
- Adapt AI for specialized use cases in healthcare, finance, law, or education (technical professionals).
- Integrate LLMs into scalable, user-facing applications (product developers and AI consultants).
Whether your goal is to build intelligent chatbots, personalized learning systems, or advanced document search tools, this program provides the applied knowledge and tools to bring cutting-edge AI into practice.
Learners who successfully complete all course requirements are eligible to earn a certificate of completion.
Note: Learners who enrolled through the SPRINGAI promotion may purchase the certificate for $20 upon successful course completion.
Course Prerequisites
Basic Python programming knowledge
What You Will Learn
By the end of this course, learners will be able to:
- Build Retrieval-Augmented Generation (RAG) Systems: Implement vector search, knowledge graphs, and context-aware workflows to improve the accuracy and relevance of LLM outputs.
- Customize and Fine-Tune LLMs: Apply fine-tuning techniques with tools such as Hugging Face and LLaMA 2 to adapt models to specific business or technical use cases.
- Deploy AI-Powered Applications: Integrate customized generative AI models into real-world web applications using tools such as LangChain, Llama-Index, and OpenAI APIs.
- Module 1: Building Custom Generative AI Retrieval-Augmented Generation (RAG)
By the end of this module, learners will be able to:
- Explain the concept of Retrieval-Augmented Generation (RAG) and its applications.
- Differentiate between human agents and LLM agents.
- Implement vector search for retrieving similar vectors.
- Build and test RAG models with synthetic data.
- Apply text analytics and knowledge graphs in generative AI.
- Module 2: Fine-Tuning
By the end of this module, learners will be able to:
- Understand the process of fine-tuning large language models.
- Differentiate various fine-tuning techniques, including adapter-based tuning
- How to fine-tune GPT models
- See how customized models can be embedded inside web applications
Instructors
Johar received an M.A. in Economics from the Birla Institute of Technology and Science and is a Fellow of the Indian Institute of Management Calcutta. He received a Ph.D. in Information Systems from the Stern School of Business, New York University in 1994. Prior to joining Columbia, Johar has worked as a quantitative trader at Morgan Stanley, Credit Suisse and Deutsche Bank, at a tech startup (MSpoke), and has taught at NYU Stern School of Business and the Gabelli School of Business Fordham University.