Data Engineer Analyst

VASANTHAGEETHAN ARPUTHARAJ

Denver CO +1-330-***-**** *******************@*****.*** www.linkedin.com/in/vasanthageethan-arputharaj Open to relocate PROFESSIONAL EXPERIENCE

Virtusa Consultancy Services Hyderabad, India

Cloud Data Engineer June 2021 - September 2022

• Built end-to-end CI/CD pipelines and designed automated workflows to migrate and transform data from Snowflake to AWS Redshift, improving accuracy, reducing deployment time by 40% while ensuring scalability and compliance with HIPAA and GDPR standards.

• Developed and optimized complex SQL queries to analyze policy trends and claims, improving query performance by 30%, and reduced latency by 25% through UDF enhancements, database query tuning, including Kafka stream configuration for real-time processing.

• Generated dashboards using Tableau and PowerBI, providing detailed insights into claims trends, which led to a 20% reduction in claim processing time and supported executive decisions affecting $50M+ in annual policy revenues.

• Streamlined workflows across development and testing teams alongside performance monitoring, improving system reliability by 25%. ITC Limited Tiruchirappalli, India

Data Analyst- Intern May 2019 - December 2019

• Built a robust ETL pipeline using AWS Glue, S3, and Lambda to process raw files into structured formats, automated CI/CD workflows, and ensured seamless data updates, reducing manual efforts by 30% and improving operational efficiency.

• Designed and managed PostgreSQL database handling, while creating insightful PowerBI dashboards to track stock flow and optimize the supply chain, resulting in a 15% reduction in material handling time.

• Maintained detailed workflow documentation using Jira, streamlining over 20 workflows, enhancing cross-functional collaboration, and boosting issue resolution speed by 20%.

• Streamlined digital workflows and optimized data accessibility across teams, showcasing problem-solving skills that reduced workflow interruptions and accelerated decision-making processes by 25%. ACAMEDIC PROJECT EXPERIENCE

GenAI based Medicare report analysis

• Developed a GenAI solution leveraging RAG (Retrieval-Augmented Generation) framework integrated with LangChain and OpenAI GPT-4 to extract insights and summarize Medicare reports, improving analysis efficiency by 30%.

• Built a web application using Flask and FastAPI to provide an interactive interface for uploading reports, querying data, and summary.

• Optimized data retrieval pipelines using vector databases for semantic search, enabling real-time querying and information extraction. Fine-tuned BERT model Movie Plot Classifier

• Fine-tuned a BERT model using Hugging Face Transformers to classify movie plots with 88% accuracy, state-of-the-art NLP techniques.

• Implemented a Streamlit web application to provide an interactive platform to query movie plots, generating real-time genre predictions.

• Developed a web scraping pipeline to gather and update movie plot datasets from reliable sources, ensuring the ml model remains latest. CG-GAN Based Image Restoration System

• Restored noisy, blurry, or aged images using advanced CG-GAN technology, achieving improvements in image quality and clarity.

• Deployed the solution on AWS SageMaker, with API access via AWS Lambda, enabling low latency for real-time image processing.

• Leveraged AWS services (SageMaker, Lambda, and S3) to build a scalable, cost-effective solution with minimal maintenance overhead.

• Integrated an intuitive frontend for seamless image upload and real-time processing enhancing user experience and accessibility. EDUCATION

Kent State University Kent, OH

Master of Science, Computer Science Graduation: Dec 2024 Sri Krishna College of Engineering and Technology Coimbatore, India Bachelor of Engineering, Computer Science Graduation: April 2021 SKILLS

Programming languages: Java, Python (Pandas, NumPy, Scikit), C, JavaScript, PL/SQL Cloud & Big data technologies: AWS (Redshift, SageMaker, Lambda, Glue, S3), Apache Spark, Snowflake Databases: MySQL, PostgreSQL, NoSQL, MongoDB

Data Visualization: Power BI, Tableau, Matplotlib

Machine Learning & AI: Supervised & Unsupervised Learning, RNN, GenAI, LLM, Pytorch, Langchain Technologies: JIRA, JUnit, Postman, FastAPI, RESTful APIs, Docker, Flask, Github actions, Git - version control CERTIFICATIONS

• Data Engineering with AWS nanodegree Udacity

• Oracle Certified Associate JAVA SE 8 Programmer

Contact this candidate