Mohan Vanukuri

Senior Data Scientist
Markel, Glen Allen, VA — Mar 2024 – Present

• Designed and implemented an enterprise-grade data warehouse architecture, integrating data from multiple sources into an EDW using Spark, Hive, and Redshift.
• Built scalable data pipelines for big data processing and machine learning use cases using Apache Spark, Python, and Hadoop ecosystem tools (HDFS, Hive, MapReduce).
• Developed and deployed NLP models for sentiment analysis and implemented advanced ML algorithms (classification, regression, clustering, dimensionality reduction) using Spark MLlib and Python.
• Improved user lifetime value by 45% and tripled conversions by applying predictive analytics and personalization techniques.
• Migrated EDW to AWS cloud (EMR, S3, Redshift), optimizing performance and cost-efficiency; configured platform architecture for scalable ML workloads.
• Managed data quality and consistency through SQL- and Hive-based validation scripts, Informatica MDM Hub, and STAR schema modeling for Tableau dashboards.
• Leveraged Teradata utilities (BTEQ, Fast Load, Tpump) and SQL across Redshift, Oracle, PostgreSQL, and MySQL for high-volume data ingestion and transformation.
• Created interactive visualizations using Python and Tableau, delivering actionable insights to business stakeholders.

Data Scientist
Vertex, Palo Alto, CA — Jan 2022 – Mar 2024

• Developed enterprise data models, data dictionaries, and metadata repositories to support master data management and data governance initiatives.
• Built and optimized large-scale data pipelines using Python, SQL, Spark, NiFi, and Kafka for real-time and batch processing in distributed environments.
• Applied advanced ML and deep learning algorithms (XGBoost, TensorFlow, PyTorch) for predictive analytics and risk modeling; conducted EDA and hypothesis testing for business strategies.
• Designed and deployed STAR schema models in Amazon Redshift; developed Tableau dashboards for actionable business intelligence.
• Led cloud data infrastructure migrations to AWS and Azure (S3, EMR, Redshift, Azure Data Lake), enhancing scalability and storage efficiency.
• Integrated NLP tools (NLTK, Stanford NLP) for text mining and unstructured data analysis; implemented clustering and optimization techniques on SQL platforms.
• Optimized query performance in PostgreSQL, MongoDB, and Cassandra; used Databricks to orchestrate ML workflows and streamline ETL processes.
• Conducted training sessions and workshops to upskill teams in modern data science practices, tools, and technologies.

Data Scientist
Finish Line, Indianapolis, IN — Oct 2019 – Dec 2021

• Built and deployed machine learning models (XGBoost, Random Forest, Neural Networks) using Python, TensorFlow, and PyTorch to solve complex business problems and enhance predictive accuracy.
• Developed real-time and batch data pipelines using Apache Spark and Kafka; automated data ingestion and transformation workflows with Python and ETL tools.
• Leveraged AWS and Azure platforms for scalable ML model deployment and managed large datasets across cloud infrastructure.
• Conducted data analysis across SQL and NoSQL systems (MongoDB, Cassandra) to support business intelligence and data strategy initiatives.
• Designed and visualized insights through interactive dashboards using Tableau and Power BI; led A/B testing and statistical experiments for model validation.
• Ensured data integrity through governance and quality controls using Alteryx and Talend; implemented best practices for data standardization.
• Managed and mentored junior data professionals, while driving knowledge sharing through documentation and collaborative work in Databricks.
• Supported strategic initiatives by aligning data architecture with organizational goals and recommending improvements based on root cause analysis.

Data Analyst / Data Modeler
Excellent WebWorld, Ahmedabad, India — Nov 2016 – Jul 2019

• Developed and implemented data mapping, transformation, and cleansing rules for Master Data Management (MDM) across OLTP and ODS environments.
• Designed conceptual, logical, and physical data models using ERWin; enforced referential integrity and collaborated with application and modeling teams for validation.
• Created OLAP metadata catalog tables and performed forward engineering for database schema generation; handled SQL-based data extraction and analysis tasks.
• Identified slowly changing dimensions and designed dimensional hierarchies to support enterprise reporting and analytics.
• Automated reporting using Teradata and ODBC connectivity to MS Excel; executed departmental performance reports using Oracle SQL and Excel.
• Conducted ad hoc analysis using BTEQ and Teradata SQL scripts; ensured efficient data exchange between flat files and databases.