About Me
I’m passionate about
Artificial Intelligence,
Machine Learning, and
Conversational Systems. My recent work centers on
Retrieval-Augmented Generation (RAG),
LangChain,
chatbot development, and intelligent system design using vector databases and LLMs (Local Ollama model). I am seeking internship opportunities where I can apply my skills, collaborate with a dynamic team, and contribute to developing innovative AI solutions.
Additionally, I am planning to pursue a master’s degree to deepen my expertise and further contribute to cutting-edge AI research and applications.
Skills
- Languages: Python, C, MATLAB
- AI/ML: RAG, LangChain, FAISS, Transformers, Scikit-learn, TensorFlow
- Web: Git, GitHub, MCP, FastAPI, Flask
- Tools: VS Code, Jupyter, Ollama, PyMOL, Notion
Experience
AI, Software, Prompt Engineer
Dec 2024 – Present
AIdenBio
— Daejeon, KR
- Designed and maintained backend systems focusing on AI model integration, API development, and database management.
- Engineered and optimized prompts for Large Language Models (LLMs) for personalized, context-aware responses.
- Developed and deployed Retrieval-Augmented Generation (RAG) pipelines improving output accuracy and relevance.
- Contributed to building intelligent, production-grade systems for life sciences and biomedical applications.
Projects
-
ChatPDB - Protein Structure Visualization Assistant (LLM + RAG + PyMOL)
An intelligent assistant that interprets natural language queries to visualize protein structures. Built with FastAPI and PyMOL for interactive 3D rendering, leveraging Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) for semantic understanding. Features a robust retriever pipeline utilizing BM25, FAISS, and Cross-Encoder with a domain-specific vector store derived from UniProt annotations. Supports session-based workflows and automated analyses including ligand binding sites, domain identification, and hydrophobicity visualization. Also includes a command-line interface powered by Ollama and Qwen/Deepseek LLMs.
-
Iris Flower Classification with Support Vector Machine (SVM)
Developed a machine learning model to classify iris flowers using SVM. Utilized Scikit-learn for training and evaluation, and visualized model performance with confusion matrices and decision boundaries.
-
Customer Segmentation with K-means Clustering
Applied K-means clustering on synthetic customer data to segment customers based on age, income, and spending score. Key steps included data scaling, determining the optimal number of clusters using the Elbow Method, and evaluating cluster quality with silhouette scores.
Education
B.E. in Electrical Engineering
Sept 2022 – Present
Chungnam National University
- GPA: 3.35/4.5
- Relevant coursework: Modern Control Theory and Design, Sensor and Measurement Engineering, Computer Programming, AI and Future Society, Computer Scientific Thinking, Information Technology of Power Systems
