• Developed and deployed machine learning models to predict customer behavior, resulting in a 20% increase in targeted marketing efficiency.• Leveraged advanced machine learning techniques such as ensemble methods to optimize recommendation systems, leading to a 25% improvement in AWS adoption.• Engineered data pipelines for feature extraction and preprocessing to support machine learning model training, ensuring data consistency and quality throughout the process.• Integrated data from diverse sources, including databases, APIs, and third-party systems.• Architected robust and scalable data integration pipelines utilizing Pyspark, orchestrating the migration from a data warehouse to a data lake ecosystem.• Executed end-to-end data responsibilities encompassing data modeling, ad-hoc analysis, and the formulation and implementation of algorithms to extract Marketing metrics within the AWS environment.• Delivered extensive support to more than 50 stakeholders, delving deep into their needs, and furnishing actionable insights to address data inquiries effectively.• Elevated data integrity and quality assurance through advanced test design and documentation, enabled self-service customer support.• Implemented data pipeline automation using CI/CD methodologies to ensure seamless and reliable ETL processes, enhancing data quality and reducing processing time.

• Worked on a DARPA-sponsored Machine Learning project whose goals were to use analog signals to detect malware in systems.• As part of the project captured electromagnetic signals using different microcontrollers as part of data collection.• Used machine learning algorithms for anomaly detection in these signals after training the model with fake signals generated using CycleGAN.

• Experienced in interpreting and analyzing data to drive the growth of top 5pharmaceutical companies in the USA.• Loaded and transformed large sets of structured and semi-structured datafrom various downstream systems.• Developed ETL pipelines using Spark and Hive for performing variousbusiness-specific transformations.• Building data applications and automating the pipelines in Spark for bulk loadsas well as Incremental Loads of various Datasets.• Worked closely with our data scientist teams and business consumers to shapethe datasets as per the requirements.• Automated the data pipeline to ETL all the Datasets along with full loads andincremental loads of data.• Wrote spark applications to perform operations like data inspection, cleaning,load, and transforming large sets of structured and semi-structured data.