Python Developer & Machine Learning Engineer focused on building end-to-end ML pipelines, scalable Python systems, and deployable data applications.
I enjoy designing modular architectures, performing structured data preprocessing, and turning models into real, usable tools through clean code and interactive dashboards.
- Programming: Python (OOP), SQL
- Machine Learning: Classification, Regression, Feature Engineering, SMOTE, PCA, Model Evaluation, Hyperparameter Tuning
- NLP: TF-IDF, Lemmatization, Tokenization, Cosine Similarity
- Libraries & Tools: Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn, Streamlit, Flask (Basic)
- DevOps / Tools: Git, GitHub, Docker (Basic), VS Code, JupyterLab, Linux (Basic)
- Core Strengths: Modular architecture, EDA, debugging, optimization, pipeline design, version-control workflows
End-to-end fraud classification pipeline with SMOTE, feature engineering, and hyperparameter tuning.
- Achieved 88% accuracy on an imbalanced dataset
- Built with modular, reusable ML architecture
- Deployed on Streamlit with real-time scoring & insights
Code: github.com/shambhuraj-patil/Fraud-Detection-App
Live Demo: https://fraud-analyzer.streamlit.app
NLP system that matches resumes to job descriptions using TF-IDF + cosine similarity.
- Automated skill extraction & role-fit scoring
- Candidate ranking + match visualization
- Deployed as an interactive Streamlit dashboard
Code: github.com/shambhuraj-patil/AI-Resume-Screening
Live Demo: https://ai-jobfit-analyzer.streamlit.app
- System monitoring tool with automated process alerts
- Customer segmentation using K-Means + PCA
- Predictive ML models: Titanic, diabetes, wine quality (structured EDA + feature engineering workflows)
ML system design, NLP workflows, deployment pipelines, scalable Python apps, and data engineering fundamentals.
- Email: shambhurajpatil27@gmail.com
- LinkedIn: linkedin.com/in/shambhurajpatil
- GitHub: github.com/shambhuraj-patil
Always building — focused on creating reliable, practical, and scalable ML solutions.