AI & Data Science undergraduate focused on building production-ready ML systems and GenAI applications.
-
Built end-to-end ML pipelines (EDA → modeling → SHAP → deployment) using MLflow, FastAPI, PostgreSQL
-
Optimized SHAP explainability pipeline → reduced memory usage from ~15GB to ~5–7GB while maintaining output accuracy
-
Designed automation systems:
- WhatsApp document verification agent (FastAPI + Twilio)
- Microsoft Teams mood-meter bot with anonymous data tracking
-
Worked on demand forecasting + model evaluation pipelines using CatBoost and business metrics
- ML Engineering & scalable pipelines
- Explainable AI (SHAP optimization)
- GenAI systems (RAG, embeddings, LLM workflows)
- Backend systems for AI applications
Languages: Python, SQL ML/AI: Scikit-learn, Pandas, NumPy, SHAP, YOLO, NLP, GenAI Backend: FastAPI, Docker, PostgreSQL, MLflow Tools: Git, Tableau, LangChain, LangGraph
-
Live Accident Detection (YOLO) Real-time detection pipeline using OpenCV + alert system
-
Research Paper Recommendation System LLM + embeddings-based recommendation with user profiling
-
Teams Mood-Meter Bot Anonymous employee sentiment tracking system with structured DB pipeline
📬 Open to opportunities in ML Engineering / GenAI / Backend AI systems