3rd-year B.E. student in AI & Data Science at PVGCOE, Nashik. I build end-to-end ML pipelines — from raw data wrangling to model evaluation — and I'm currently going deep into Generative AI: LangChain agents, RAG pipelines, and tool-use patterns.
I treat projects as the real curriculum. Everything below is something I've built and can walk through.
Machine Learning
- Supervised learning: Logistic Regression, Linear Regression, Decision Trees, Random Forest
- Full pipeline ownership: EDA → feature engineering → preprocessing → training → evaluation (F1, accuracy, confusion matrix)
- Libraries: Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn
Generative AI (actively building)
- LangChain agents & chains
- Tool-use and multi-step reasoning
- Prompt engineering for structured outputs
Python & Web
- Flask & FastApi — auth systems, REST routes, ORM with SQLAlchemy
- SQL — schema design, joins, aggregations
- Git — version control, branching, collaboration
Confident enough to teach:
Python & OOP · Pandas / NumPy · Matplotlib / Seaborn · Scikit-learn · Flask / FastApi · SQL · Git
OpenBuild — Build-in-public web platform
Full-stack Flask app where users document and share project progress on a community feed. Includes user auth, project CRUD, and AI-generated project summaries via LLM integration.
Flask·SQLAlchemy·Python·HTML/CSS·LLM API
Student Performance Classification — Multi-class ML project
Predicts student performance (Low / Medium / High) from academic features. Full pipeline: EDA, feature engineering, training Logistic Regression vs Random Forest, F1-score comparison across classes.
Scikit-learn·Pandas·Seaborn·Python
+ college mini-projects & experiments → View all repositories ↗
- 🔧 Going deeper into LangChain agents — tool calling, memory, multi-agent patterns
- 📖 Strengthening statistics & probability fundamentals for ML theory
- 🏗️ Building more public projects to document the learning
Open to internships in ML Engineering, Data Science, or Gen AI · Nashik, India · Graduating 2027