Applied AI Engineer focused on:

• Real-time AI Systems
• Data Infrastructure
• Human-Centered Analytics
• ML Inference & Backend Engineering

I enjoy building deployable AI systems that connect machine learning, backend infrastructure, and real-world data workflows.

• Real-time AI serving systems
• Data pipelines & analytics infrastructure
• Human behavioral & biosignal analytics
• AI backend engineering with FastAPI & Docker

AI-powered real-time focus analytics platform using computer vision and optimized inference serving.

• K-Softvation 2025 Grand Prize
• CLIP-based automated labeling pipeline
• AUC 0.997 / F1 0.963
• ONNX optimized inference serving
• FastAPI + WebSocket real-time architecture

Python · PyTorch · FastAPI · ONNX · WebSocket · Docker

AI agent system for macroeconomic time-series analysis based on VARX statistical methodology.

• LangGraph-based AI workflow
• Statistical causal analysis pipeline
• Streamlit deployment
• Time-series analytics automation

Python · LangGraph · statsmodels · Streamlit · Time-Series Analysis

Real-time posture and forward-head posture monitoring system using webcam-based computer vision.

• Human posture analytics
• Real-time inference
• Behavioral monitoring system

Python · SQL · R

FastAPI · PostgreSQL · Docker · Redis · Linux

PyTorch · Scikit-learn · ONNX · LangGraph

Pandas · NumPy · statsmodels · Time-Series Analysis

• Applied AI Systems
• AI Infrastructure
• Data Engineering
• Human State Analytics
• AI for Healthcare & Productivity

• GitHub: https://github.com/kunoong
• LinkedIn: (update soon)
• Email: (your email)

“AI becomes valuable only when it is connected to reliable systems, usable data, and real-world workflows.”