NLP & Large Language Models
Transformers · RAG · Prompt Engineering · Fine-tuning · Multimodal · Text Mining
Education
Building AI systems builders, not just AI users.
Courses are structured around working systems, from language models and agents to deployment, monitoring, and responsible use.
Team-based capstone project — reinforcement learning for rocket guidance, satellite data applications, computer vision, and AI agent systems in aerospace domains.
Designing, building, and validating AI models as operational systems — AIOps, agent systems engineering, and deployment.
Knowledge representation and AI fusion — ontology-first thinking, decision science, semantic modeling, and generative AI critical analysis. AI Aerospace specialization track.
Programming collaborative robots — system installation, operation, pick & place, and palletizing workflows.
ML systems in production — DevOps, MLOps, security practices with Docker, Kubernetes, and CI/CD.
OS design and management — process management, memory, file systems, and Linux through hands-on labs.
DevOps principles and tools — cloud computing, containerization, CI/CD, and agile methodologies.
Data science in economics and finance — ML, text mining, and network analysis for forecasting.
Architecture, application paradigms, and ethics of LLMs — hands-on training, paper analysis, and practical development.
Transformers, attention mechanisms, tokenization, and LLM fine-tuning with hands-on exercises.
Software development lifecycle with Python — coding, testing, deployment, and maintenance.
AI and ML applications in banking, insurance, and investment — case studies and industry lectures.
Designing and implementing ML systems — DevOps, MLOps, CI/CD, model deployment and monitoring.
Recent advances in AI and NLP through influential research papers — neural networks, sequence modeling, generative models, and transformers.
Deep learning techniques for NLP — pre-trained language models and fine-tuning with PyTorch and Hugging Face.
Fundamentals of NLP — text pre-processing, syntax, semantics, classification, topic modeling, and embeddings.
High school AI course at Daejeong Girls' HS — AI concepts, ChatGPT/Claude, Python, and inquiry-based problem solving.
NLP techniques for social science researchers — leveraging LLMs to analyze textual data and address research questions.
Transformers · RAG · Prompt Engineering · Fine-tuning · Multimodal · Text Mining
AIOps · Agent Orchestration · Governance · Responsible AI
Docker · Kubernetes · CI/CD · Model Deployment · Monitoring
Linux · Concurrency · Containers · Scheduling · AI Accelerators
Collaborative Robots · Automation · Edge AI · Pick & Place
FinTech · Economics · Algorithmic Trading · Network Analysis
Aristotle's entelecheia, the drive toward full actualization, guides how I design courses. AI education should not produce tool users; it should cultivate systems builders who understand the full stack from model training to production deployment, from data pipelines to responsible governance.
Every course centers on building real systems. Students deploy ML models behind APIs, orchestrate agent workflows, monitor production services, and confront the engineering trade-offs that textbooks abstract away. The goal is that by graduation, they have shipped, not just studied.
In an era where AI agents can write code and automate workflows, the differentiating skill is judgment: knowing what to build, when to intervene, and how to align systems with human values. That is the entelecheia of AI education, technology reaching its purpose through the people who shape it.