I design, optimize, and deploy AI models as scalable, production-ready services.
Focused on model serving, inference optimization, and system-level integration.
- PyTorch
- LSTM / CNN
- Model Quantization
- ONNX
- FastAPI
- REST API
- Async Processing
- Logging System
- Docker
- AWS EC2
- GitHub Actions
- C / C++
- Linux
- fork / exec / pipe
- Process Management
- AI Model Serving Platform β FastAPI + Docker κΈ°λ° λͺ¨λΈ μλΉ μμ€ν
- MLOps Automation Pipeline β μλ νμ΅ λ° λͺ¨λΈ λ²μ κ΄λ¦¬ μμ€ν
- Linux Task Manager β fork/exec κΈ°λ° νλ‘μΈμ€ κ΄λ¦¬ νλ‘κ·Έλ¨
- Sports Motion Analysis AI β LSTM κΈ°λ° λμ λΆμ λͺ¨λΈ
- AI Inference Optimization
- Scalable API Architecture
- MLOps & Automation
- AI + System Integration
π§ hoho990312@naver.com