Tanuja S

Experience

• 

  IBM

  Jun 2019 - Jul 2022

  • Designed and developed ETL pipelines to process large-scale data from multiple sources.• Automated data ingestion, transformation, and loading processes, ensuring high efficiency and reliability.• Optimized ETL workflows to reduce processing time and improve system performance.• Built and maintained data warehouses, ensuring structured and efficient data storage.• Designed data models to support business intelligence (BI) and analytics needs.• Used SQL to perform complex queries, optimize database performance, and ensure data integrity and optimized SQL queries for data extraction, transformation, and reporting.• Implemented indexing and query tuning strategies to enhance database performance.• Created stored procedures and functions to automate repetitive data processing tasks.• Developed Python scripts to automate data transformation and cleansing processes and used Pandas, NumPy, and other libraries to process and manipulate large datasets.• Integrated Python with SQL databases and AWS services for seamless data handling.• Designed and implemented AWS-based data pipelines using services like S3, Glue, Redshift, and Lambda and leveraged AWS Lambda for serverless data processing and automation.• Managed and optimized data storage and processing in cloud environments.• Transformed raw data into meaningful insights using visualization tools and developed dashboards and reports to support data-driven decision-making.• Ensured stakeholders had access to real-time data insights for business operations. Show less • Partnered with stakeholders to understand business needs, define key performance indicators (KPIs), and translate them into actionable insights.• Conducted in-depth data analysis to identify trends, anomalies, and opportunities for process optimization.• Provided strategic recommendations based on data insights to support operational efficiency and business growth.• Created dynamic reports with advanced DAX calculations to analyze complex datasets.• Optimized visualizations to improve decision-making by enhancing readability and usability for stakeholders.• Wrote and optimized PL/SQL queries to extract, transform, and load (ETL) large datasets efficiently.• Built complex SQL queries for in-depth data analysis and reporting.• Worked with relational databases to maintain data integrity and optimize query performance.• Developed Python scripts to automate data extraction, transformation, and reporting processes, reducing manual effort.• Implemented data cleansing techniques using Python to enhance data accuracy and reliability.• Used object-oriented programming (OOP) principles to structure code for reusability and scalability.• Utilized Git for version control, ensuring seamless collaboration and tracking of changes in data analysis projects.• Worked in an Agile environment, contributing to sprint planning, daily stand-ups, and retrospectives.• Created detailed technical documentation for dashboards, SQL queries, and data workflows to ensure knowledge transfer and scalability and documented business requirements for data analysis and reporting projects.• Conducted product data analysis to evaluate performance metrics and drive improvements.• Used Excel and Google Sheets for quick data analysis, pivot tables, and advanced formulas and integrated Power BI with spreadsheets for ad-hoc reporting and deeper insights. Show less

  • Data Engineer | IBM (T-Mobile Client)

    Jun 2020 - Jul 2022

  • Power BI & Data Analyst | IBM (Google Client)

    Jun 2019 - Jun 2020
• 

  Kent State University

  Aug 2023 - May 2024

  Graduate Assistant | Kent State University

  • Designed and implemented machine learning models for predictive analytics and decision-making.• Performed feature engineering, hyperparameter tuning, and model evaluation to enhance performance.• Developed and tested models for classification, regression, and clustering using Scikit-Learn, TensorFlow, and PyTorch.• Researched and implemented Generative AI models, including text generation and image synthesis and fine-tuned large language models (LLMs) for domain-specific applications.• Applied prompt engineering techniques to optimize AI-generated responses.• Built and trained neural networks (CNNs, RNNs, Transformers) for image recognition and sequence modeling.• Worked on computer vision applications such as object detection, facial recognition, and image classification using OpenCV and TensorFlow.• Optimized deep learning models for real-time inference and deployment and developed text classification, sentiment analysis, and chatbot models for various applications.• Preprocessed and analyzed large-scale textual data using NLP libraries like NLTK, SpaCy, and Hugging Face Transformers.• Implemented topic modeling and named entity recognition (NER) for structured text extraction and deployed machine learning models using AWS, Google Cloud AI, and Azure ML.• Integrated MLOps practices, including model versioning, CI/CD, and API deployment and built end-to-end AI pipelines for automated model training and inference.• Processed large datasets using Spark and Hadoop for efficient AI model training and conducted exploratory data analysis (EDA) and statistical modeling for data-driven insights. Show less