Sheri Keerthi Reddy

About Sheri Keerthi Reddy

Data Scientist and Machine Learning enthusiast with a proven track record of transforming complex data into actionable insights. Currently pursuing an MS in Data Science at the University of Michigan-Dearborn, I bring hands-on experience as an Associate Data Analyst at Accenture, where I significantly improved business processes and decision-making through data-driven solutions. My expertise spans the entire data science pipeline- Data Analysis & Visualization: Proficient in Python, R, SQL, Tableau, and Power BI - Machine Learning: Skilled in TensorFlow, Keras, and scikit-learn for building predictive models - Big Data Technologies: Experienced with Hadoop, MapReduce, Hive, and PySpark - Statistical Analysis: Well-versed in hypothesis testing, A/B testing, ANOVA, and various regression models Key Achievements- Developed a multilingual text summarization system using advanced NLP techniques - Implemented a CNN model for traffic sign classification with 97% accuracy - Created a real-time web analytics dashboard for BestBuy, improving product performance analysis - Optimized insurance claims processing, resulting in a 15% decrease in processing time and 20% increase in efficiency I\'m passionate about leveraging cutting-edge technologies to solve complex business problems. My academic background in Computer Science Engineering, coupled with my ongoing Data Science studies, provides me with a strong foundation in both theoretical concepts and practical applications. I thrive in collaborative environments and have a proven ability to communicate complex technical concepts to non-technical stakeholders. Whether it\'s developing machine learning models, conducting statistical analyses, or creating intuitive data visualizations, I\'m committed to delivering high-quality results that drive business value. Currently seeking opportunities to apply my skills in Data Science and Machine Learning roles. I\'m particularly interested in positions that allow me to work on challenging problems in areas such as natural language processing, computer vision, or predictive analytics. Let\'s connect if you\'re looking for a data scientist who combines technical expertise with business acumen and a passion for innovation!

Experience

1. Cloud Data Engineer

   Kroger

   Mar 2025 — Present

   ETL Development & Data Ingestion:Designed and maintained scalable ETL frameworks using AWS Glue, Azure Data Factory, and Apache Airflow, handling diverse structured and semi-structured data from sources like PostgreSQL, Oracle, SQL Server, MongoDB, JSON, XML, DB2, and Apache Iceberg.Data Processing & Transformation:Utilized Azure Databricks and Apache Spark with Python notebooks and regular expressions to parse complex policy documents and perform high-volume data transformations. Integrated Spark with NoSQL databases like HBase for real-time data processing.Cloud Architecture & Integration:Built and managed cloud-native architectures using Azure Synapse Analytics, AWS S3, and Snowflake, ensuring efficient data storage, cataloging, and retrieval. Developed secure, modular data lakes and integrated analytics solutions with AWS Redshift and QuickSight.Streaming & Real-Time Data Engineering:Engineered robust real-time data pipelines using Kafka and Apache Spark, optimizing for high throughput and minimal latency. Applied dynamic partitioning strategies to enhance query performance and resource efficiency.Analytics, Reporting & Visualization:Created automated reporting dashboards using Power BI and Tableau, delivering real-time insights and supporting advanced analytics use cases.Data Modeling & Quality Assurance:Specialized in data modeling, resolving data integration challenges, standardizing inconsistent data formats, and validating the effectiveness of new data sources and gathering methods.

Education

• University of Michigan

  Master of Science - MS

  2023 — 2024

• Osmania University

  Bachelor of Engineering - BE

  2017 — 2021