Experience
Data Scientist — Scipy Technologies (Remote)
May 2025 – Present- Built and optimized end-to-end machine learning and deep learning models using Python, Scikit-learn, TensorFlow, and Keras.
- Designed and validated Retrieval-Augmented Generation (RAG) pipelines, achieving 90%+ faithfulness and context recall using RAGAS-based evaluation.
- Improved document retrieval quality by removing near-duplicate content across 400+ PDFs using TF-IDF and SBERT embeddings, reducing retrieval noise and improving grounding consistency.
- Engineered a CPU-only real-time vision pipeline for edge deployment, achieving ~8.9 FPS with stable multi-person tracking.
- Diagnosed data leakage and class imbalance during EDA and implemented corrective feature engineering strategies, improving Precision, Recall, and F1-score.
- Built end-to-end ML pipelines from data ingestion to lightweight deployment using Python, FastAPI, SQLAlchemy, and Streamlit.
Enterprise Development Executive — District Industries Centre
Apr 2022 – Mar 2025- Analyzed a 10,000+ row enterprise dataset to support onboarding and evaluation of 500+ enterprises, contributing to full target achievement.
- Built Excel-based monitoring dashboards (Pivot Tables, performance tracking, fund utilization).
- Generated structured analytical reports for district-level decision-making.
Academic Assistant — SMEG Edulabs
Oct 2020 – Mar 2022- Built a facial recognition attendance system using OpenCV with automated CSV-based logging.
- Developed an SMS spam detection model using TF-IDF + Scikit-learn, achieving ~96% precision.
- Mentored students on ML mini-projects covering preprocessing, EDA, and evaluation.
Trainer — EduBridge India
Jan 2020 – Jun 2020- Trained 100+ students in data analysis, Excel-based reporting, and numerical reasoning.
- Delivered hands-on sessions using PivotTables, VLOOKUP, and conditional formulas.