Experience

Sam's Club

• United States
• Retail
• 300 - 400 Employee

• Senior Machine Learning Engineer

  • Mar 2022 - Present

  United States Developed Cluster model for trailer forecast Sam's Supply Chain Analytics Contributed the feature Sams store framework for MLOPS Lead the team and developed for Midterm IDC Flow forecasting Developed model pipeline for GDC Out pallets vs full pick use cases. Developed the data quality framework for sams supply chain Developed pipelines in Azure MLOPS and Azure data factory, Databricks



Walmart

• United States
• Retail
• 700 & Above Employee

• Senior Data Scientist

  • Jun 2020 - Mar 2022

  Bentonville, Arkansas, United States • Setup Analytics model data pipeline time sensitive busy families (TSBF) and budget sensitive busy families (BSBF) and CLTV model • Created high level architecture for third party data services. • Re-Architecture the Sales Order Line module with petabyte volume of data and saved GCP cost by 50%. • Increased the efficiency of the program and automated about 50% reports using Super set, Metabase dashboards. • Data Ingested with various source system optimized the airflow… Show more • Setup Analytics model data pipeline time sensitive busy families (TSBF) and budget sensitive busy families (BSBF) and CLTV model • Created high level architecture for third party data services. • Re-Architecture the Sales Order Line module with petabyte volume of data and saved GCP cost by 50%. • Increased the efficiency of the program and automated about 50% reports using Super set, Metabase dashboards. • Data Ingested with various source system optimized the airflow pipeline in python by 2% batch process. • Developed the python cluster manager to support data analyst to increase productivity by 30%. • Led cloud team, super set dashboard for Big Query cost monitoring to save GCP cost around $3 million. • Implemented the HTTPS and SSL certificate (SSL offloading for dashboard servers) using NGINX. • Implemented the Google storage services with AWS migration to ingest the data and saved cost around $1 million. • Participate in support and engineering meetings to escalate any critical issues to engineering. • Implemented GCP monitoring dashboard such as Deployment version dashboards and Cost dashboards. • Independently own and address and resolve applications issues, provide updates and perform root cause analysis. • Developed CI/CD administration includes GIT repository creation, Jenkins Configurations and access control. • Implemented Java restful services to integrate the LDAP authentication.

• Senior Software Engineer

  • Feb 2018 - Jun 2020

  Bentonville • Worked on machine learning algorithms for assortment analytics such as Customer Decision Tree, Affinity, Loyalty, clustering algorithms using Spark, Hadoop framework scaled around peta bytes volume of data. • Implemented analytics pipeline for XGBOOST Model in Spark for assortment endcap features to scale up 3 million Items for all department and category level. • Developed Assortment optimization tool (AOT) to automate the data pipeline by 90%. • Supported Assortment workshop… Show more • Worked on machine learning algorithms for assortment analytics such as Customer Decision Tree, Affinity, Loyalty, clustering algorithms using Spark, Hadoop framework scaled around peta bytes volume of data. • Implemented analytics pipeline for XGBOOST Model in Spark for assortment endcap features to scale up 3 million Items for all department and category level. • Developed Assortment optimization tool (AOT) to automate the data pipeline by 90%. • Supported Assortment workshop process for business reports and reduced from 5 days process to 1 day. • Azure developed analytics pipeline using data bricks and data factory for proof of concept. • Developed the Java restful microservices to enable the Spark thrift services as near real time services • Implemented Java Active MQ publish and listener broker between the front and back-end applications. • Implemented the Spring boot micro services used as service layer for front end applications.

• Programmer Analyst

  • Jun 2016 - Feb 2018

  • Created Data as a Service for all BI / Data Science projects which uses on Prem Hadoop environment • Created an associate Customer 360 platform for US and later rolled it at global scale • Implemented Data governance processes and tools to ensure both the quality of data and also standardizing the metrics / KPIs • Emphasis on data security at rest and in motion (dealing with PII data) • Worked with cross functional teams on a data visualization - Implemented on-premise strategy… Show more • Created Data as a Service for all BI / Data Science projects which uses on Prem Hadoop environment • Created an associate Customer 360 platform for US and later rolled it at global scale • Implemented Data governance processes and tools to ensure both the quality of data and also standardizing the metrics / KPIs • Emphasis on data security at rest and in motion (dealing with PII data) • Worked with cross functional teams on a data visualization - Implemented on-premise strategy for Big Data on perm to Scale Peta Bytes of data - Machine Learning to scale up algorithms such as Clustering, Xboost in Spark - Implemented the micro services in Spark Thrift server to enable real-time queries.



Tata Consultancy Services

• India
• IT Services and IT Consulting
• 700 & Above Employee

• Big data Lead, Walmart

  • Nov 2015 - Jun 2016

  Bentonville • Created high level architecture to store Customer Analytics Record (CAR) and Customer Knowledge Platform (CKP) and ingested around 12 peta bytes of data. • Implemented the Customer last mile’s location algorithm in MapReduce to compute distance using Haversine formula and identified the customer last mile’s location. • Ingested around 10 terabytes volume of data in Sqoop/oozie process and optimized the queries in data lake. • Created data lake exporting data form Oracle to Hadoop… Show more • Created high level architecture to store Customer Analytics Record (CAR) and Customer Knowledge Platform (CKP) and ingested around 12 peta bytes of data. • Implemented the Customer last mile’s location algorithm in MapReduce to compute distance using Haversine formula and identified the customer last mile’s location. • Ingested around 10 terabytes volume of data in Sqoop/oozie process and optimized the queries in data lake. • Created data lake exporting data form Oracle to Hadoop data Lake ETL jobs. • Led the design and development with client and offshore team for data lake application. • Member Engagement Platform (MEP) is to automate Sam’s Membership campaign using web based front end and Hadoop as backend and improved efficiency by 30% • Automated and productionized the models such as Clustering, Propensity Score, Basket Categorization, Offer Assignment, Backfill and Campaign Measurement. • Developed the MapReduce in Java for Customer Last mile delivery Show less



The Home Depot

• United States
• Retail
• 700 & Above Employee

• Senior Web Application Developer, Home depot, USA

  • Nov 2013 - Oct 2015

  • Developed data cleansing scripts, ETL using bigdata technologies/ Informatica. • Design and Development of Item Management Java Application for Home Depot Applications. • Develop web application using FLEX and Adobe framework. • Normalized SQL database conforming to design concepts and best practices.



Target

• United States
• Retail
• 700 & Above Employee

• Web Developer Data Lead, Target

  • Dec 2011 - Nov 2013

  Chennai Area, India • Developed data cleansing scripts and web services using Spring and restful services • Created catalog applications for data service layer using java and spring, Hibernate.



Sella Synergy India Limited

• Software Engineer

  • Dec 2006 - Dec 2009

  Chennai • Developed Internal rating system as web application. • Implemented Java patterns such as query decorator, composite pattern for PEP applications. • Normalized SQL database conforming to design concepts and best practices.