Machine Learning Engineer @ oumi.ai • CS @ University of Cincinnati (2022–2027)
- ML engineering: training/eval pipelines, dataset & experiment tooling, model debugging.
- Interests: interpretability, LLMs, applied deep learning, and reliable software systems.
- Always open to: research collabs, OSS contributions, and impactful ML engineering projects.
Languages: Python, JavaScript, C++, C, Rust
ML: PyTorch, HuggingFace Transformers, scikit-learn
Web/Backend: Flask, Django, Node.js, React
Infra/Tools: Git, Docker, Postgres, PyTest
- Physical Therapy Platform (CV + Web): Visual-based exercise guidance (React, Flask API, Postgres).
- Fake News Classifier (NLP): BERT + classical ML baselines (XGBoost/RandomForest/etc.).
- Sentiment Analysis (DistilBERT): Fine-tuned on IMDB using HuggingFace Trainer.
- Apple Stock Forecasting: PyTorch LSTM time-series model.
- MNIST from Scratch: Neural network built without DL libraries (~95% accuracy).
- Software Developer — iCDCU Lab @ UC (Jan 2023 – Present)
Research Project Management System (Flask, jQuery, SQLite) - Machine Learning Intern — Kinetic Vision (May 2025 – Aug 2025)
Deep learning training + data pipelines (PyTorch, Postgres, PyTest) - Software Engineering Intern — Phillips Edison & Company (Jan 2024 – Dec 2024)
SQL automation + enterprise web apps + GenAI apps (OpenAI, LangChain)