Prathamesh Kadam Email & Phone Number

Chicago, IL, US

New York, NY, US

New York, NY, US

• Led a team of 3 data engineers in designing and implementing scalable data pipelines and ETL processes to support data collection and business intelligence initiatives for Amazon
• Developed Generic File Processing function in AWS Lambda to process different types of files into Snowflake and scheduled it to run on a daily basis using AWS Step Functions and AWS EventBridge
• Developed SQL Stored Procedures in Snowflake for generating feed files for different offline channels i.e. TV, Radio, Out of Home, Print for the US region to be sent to Amazon
• Built Continuous Delivery (CD) pipelines with GitHub for deploying Snowflake scripts from DEV to PROD environments using GitHub actions
• Ensured data quality and consistency through the implementation of data governance frameworks

New York, NY, US

• Performed enhancements on Rufus Data Manager (RDM), a Django based web application used by the global Initiative teams for Marketing Mix Modeling for Amazon
• Provisioned and maintained three AWS EC2 instances (DEV, UAT and PROD) for running the RDM application
• Developed a state machine in AWS Step Functions to ingest MediaTools (Planning data) and DCM/Sizmek (Ad Server data) into RDM
• Built Continuous Delivery (CD) pipelines with AWS CodePipeline service for deploying Rufus Data Manager (RDM) code from DEV to PROD environments
• Migrated code repositories from GitLab server to AWS CodeCommit for scalability

Boston, Massachusetts, US

• Developed personalization recommender systems on reference (graph DB) data using gremlin queries that impact more than 70K global employees of Publicis Groupe
• Developed clustering machine learning models for recommending jobs to more than 70K global employees of Publicis Groupe
• Achieved ~80% ETL efficiency for loading data from Google Analytics into Azure Databricks by setting up Spark jobs
• Built and automated dashboards in Power BI for CEO's daily report and general feature usage dashboards of Marcel Platform
• Developed ETL pipelines in Azure Data Factory (ADF) for loading reference (graph DB) and online data (Google Analytics) in Azure Data Lake Gen2 Storage
• Built and automated dashboards in Power BI for Global Marketing Team to track Audience participation for their growth webinars conducted through Zoom meetings

Oakbrook Terrace, IL, US

• Developed pipeline using Python, Spacy and NLTK packages to remove Protected Health Information (PHI) by pattern recognition
• Automated de-identification process to remove PHI from patient safety reports by deploying the pipeline in Azure ML platform
• Reduced time taken to de-identify reports by 27 hours for every 1000 reports run by implementing an NLP solution
• Developed a web application to integrate the NLP solution with Joint Commission ecosystem using JavaScript and REST APIs

Paris, France, FR

• Client: General Electric Aviation (GE Aviation)
• Trained time series models using ARIMA in Python for demand forecasting of sales data
• Prioritized and performed root cause analysis on major production issues reducing overall incident rate by 60%
• Created user stories in JIRA and performed bug fixes that resulted in 40% process improvements
• Identified and resolved 200 defects using Agile methodologies that increased application efficiency by 30%

Schaumburg, Illinois, US

• Drove customer engagement by analyzing social media data and text mining of ~ 20,000+ tweets using R
• Strategically advised clients to enhance online brand exposure by 22% by gathering competitive intelligence from various social media platforms

Paris, France, FR

• GE Healthcare: Implemented a disease diagnosis process for early detection of patients with high risk of cardiovascular disease by using a logistic regression model in Python with 81.48% accuracy and an AUC score of.
• GE Capital: Evaluated the credit risk of future customers by developing predictive models like Decision trees and Random Forest using historical customer data in R; generated customer segmentation dashboards in Tableau.
• GE Aviation: Minimized data migration downtime by 30% by conducting statistical analysis on Purchase orders, Requisitions & Invoices data; created pivot tables, charts, graphs in Excel and provided recommendations on.
• Designed and implemented ETL workflows involving the extraction of $2B transactional data from legacy systems, integration and mapping before loading into data warehouses and Oracle E-Business Suite R12 using SQL.
• Generated dashboards in Tableau to report on key metrics & KPIs in Order Management and Accounts Receivable processes

Master Of Science - Ms, Management Information Systems

Bachelor Of Engineering (Be), Electronics And Telecommunication Engineering