Bridging the gap between exploratory data science and production-grade machine learning APIs.
I started as a pure data enthusiast, fascinated by what tabular data could reveal using Pandas and Seaborn. Over time, that evolved into building predictive models.
I realized that a model alone isn't a product. Today, my focus is strictly on Machine Learning Engineering—containerizing logic in Docker and serving it via highly concurrent FastAPI endpoints.
Architecting backend AI systems, fine-tuning LLMs, and building predictive analytics pipelines for startups.
Handled massive EDA and predictive modeling tasks utilizing XGBoost and Scikit-Learn.
Focus on Data Structures, Algorithms, Mathematics, and Artificial Intelligence.
The core technologies I utilize to construct and deploy intelligent systems.
Fine-tuned DistilBERT containerized in Docker and served through FastAPI for a production-ready sentiment engine.
XGBoost classifier analyzing 10k+ rows of Telco data with SHAP explanatory analytics for business logic.