About Me
Data Analyst & Analytics Engineer with 2.8 years of enterprise experience at TCS managing high-volume data validation, ETL, workflows, and reporting views. Holds a Master’s in Data Science with hands-on expertise in Python, Power BI, SQL query optimization, machine learning, and workflow automation. Skilled at bridging enterprise data engineering with business intelligence to ensure 99%+ dataset accuracy for executive decision-making.
Skills & Technologies
Work Experience
Data & Analytics Engineer
Designed and optimized complex SQL/PL-SQL queries and stored procedures for high-volume PepsiCo inventory management systems, improving reporting accuracy and query performance. Automated ETL data pipelines and batch data validation workflows, ensuring accurate datasets for executive dashboards. Resolved critical business data issues using ServiceNow under strict SLAs, minimizing downtime. Awarded “Active Team Player" by PepsiCo client leadership for outstanding analytics delivery and support.
Graduate AI & Analytics Intern – AdM-DM Project
Analyzed real-world academic datasets to build a machine learning admission prediction model achieving over 90% accuracy. Conducted data validation, EDA, and feature engineering using Python. Trained and evaluated regression models with Scikit-learn using R2, RMSE, and cross-validation. Produced analytical reports and visualizations for academic decision-support and publications.
Volunteer Data & Analytics Specialist
Performed EDA and data cleansing on organizational datasets using Python to identify trends. Designed interactive dashboards and summary reports to communicate insights to non-technical stakeholders. Managed data validation and quality checks to ensure accuracy. Collaborated with cross-functional remote teams in Agile environment to develop predictive data models supporting strategic decisions.
Projects
AI Knowledge Assistant (RAG-Based LLM Application)
Architected an end-to-end RAG pipeline using LangChain, FAISS vector database, and Llama 3.3 for contextual Q&A over unstructured document datasets. Integrated API layers and prompt guardrails for automated question generation, profile scoring, and resume-job description semantic matching.
Tweet Sentiment Analysis & Data Pipeline
Processed and analyzed over 1 million data records using NLP preprocessing pipelines; trained sentiment classification models (Naive Bayes, Logistic Regression) achieving 90%+ accuracy. Automated ETL ingestion workflows and scheduled data pipelines using Apache Airflow deployed on AWS EC2.
Real-Time Computer Vision Analytics System
Developed and deployed a real-time computer vision system using OpenCV and TensorFlow, achieving 95% detection accuracy. Processed multi-sensor data streams, trained CNN models, and built an interactive Tkinter UI for real-time reporting.
Education
Masters of Science
Data Science
Bachelors of Technology
Electronics and Communication Engineering