About Me
👋 Hi, I’m Minseo Choi
I’m a Computer Science sophomore at Johns Hopkins University, deeply passionate about Applied ML/DL, Machine Learning Systems (MLSys), compilers, and GPU optimization.
🔬 Research & Interests
- Machine Learning Systems: Toy ML compiler projects, LLVM/MLIR exploration, GPU kernel optimization (CUDA/Triton).
- Deep Learning: Implementations of ResNet, Transformer, EfficientNet from scratch in PyTorch.
- Applied ML: Hackathon experiences (e.g., LG Aimers, Kaggle), XGBoost + Optuna hyperparameter tuning.
- Systems & Hardware: Multi-monitor workstation builds, Arch Linux ARM, virtualization, OS tinkering.
📂 Projects
- LLVM Kaleidoscope Implementation: A toy compiler implementing a lexer, parser, AST, LLVM IR generator, and JIT compilation.
- Korean-English Translation: Transformer-based MT achieving 29.9 BLEU on AI-Hub dataset.
📫 Contact
Feel free to reach out via LinkedIn or check my work on GitHub.