Data professional with logistics operations background and 1+ year of ML internship + project work. I build complete pipelines—from EDA and feature engineering to deployment—focused on practical impact.
Machine Learning Engineer with hands-on experience building end-to-end AI/ML solutions, from data preprocessing and feature engineering to model deployment. Skilled in Python, Scikit-learn, XGBoost, Pandas, Streamlit, and data visualization tools, with experience developing real-world predictive systems for logistics, restaurant analytics, CO₂ emission forecasting, and price prediction. Built and deployed multiple live ML applications on Hugging Face Spaces, including shipment delay prediction and recommendation systems. Previously worked in logistics and operations, bringing strong domain knowledge in supply chain workflows and data-driven decision-making. Passionate about solving business problems using machine learning, analytics, and scalable AI solutions.
The tools I use to turn problems into products.
Selected end-to-end builds with live deployments.
ColumnTransformer + Pipeline architecture for consistent preprocessing. Achieved R² 0.995 and RMSE ~1013. Resolved deployment issues including serialization errors, dependency conflicts, and artifact handling.
Analyzed 9,551 restaurants across 15+ countries for rating prediction, cuisine classification, and personalized recommendations (TF‑IDF + cosine similarity). Built Folium maps and deployed the full Streamlit app.
Focused on building end-to-end AI systems—from data pipelines and model training to deployment and RAG-based applications. Open to Machine Learning Engineer roles and collaborations involving applied AI, MLOps, and analytics-driven solutions.