ML Engineer | MLOps | Building intelligent systems end-to-end
I design and build machine learning systems — from data generation and model training to deployment, serving, and monitoring. I care about the full lifecycle: clean data pipelines, reproducible experiments, and production-ready infrastructure.
| Machine Learning | Python, scikit-learn, PyTorch, TensorFlow, Pandas, NumPy |
| MLOps & Infrastructure | MLflow, DVC, Docker, FastAPI, Streamlit |
| Modeling | Regression, Random Forests, Gradient Boosting, Neural Networks (MLP, LSTM/GRU), Reinforcement Learning |
| Tools | Git, REST APIs, CI/CD |
A clinical data pipeline for the CTN-0094 dataset — substance use disorder treatment research. Building reproducible ETL workflows for patient-level clinical trial data, with automated data validation, transformation, and analysis pipelines.
- MLOps — designing and building reproducible, production-grade ML pipelines
- CTN-0094 Pipeline Research — clinical data pipeline development and analysis for substance use disorder treatment research
- End-to-end ML systems — from experiment tracking to containerized deployment