Vivek Kulkarni Email & Phone Number

Bengaluru, KA, IN

Pune, Maharashtra, India

• Worked on Python backend code development for automating release management processes between SharePoint, JIRA, and SQL databases on Azure.
• Extensively worked on Azure Logic App and its integration with other services; successfully set up, data validation checks and success / failure email notification functionality.
• Implemented code vulnerability tools like SNYK, TruffleHog, and Fortify in GitHub CI / CD action and created automatic JIRA ticket creation for any vulnerability found.
• Built Data Audit & Governance solutions using GitHub REST API and GitHub Actions

Pune, Maharashtra, India

• Designed and implemented an AWS Lambda-based solution to notify teams via Slack when ECS tasks were completed, utilizing the Python programming language and the boto3 library.
• Utilized GitLab to construct robust Docker images and implement efficient CI/CD pipelines, and successfully integrated them into an AWS environment.
• Developed a comprehensive infrastructure solution using AWS CloudFormation, utilizing JSON and YAML templates to automate the provisioning and management of resources.

Chennai, Tamil Nadu, India

• Designed and implemented efficient ETL solutions for client "Benson Hill Biosystems" utilizing the full capabilities of the AWS ecosystem.
• Leveraged Terraform as an infrastructure as code tool to manage the entire lifecycle of infrastructure effectively and efficiently.
• Developed, administered and executed AWS Lambda functions and AWS Step functions, effectively utilizing Cloudwatch for monitoring and logging.

Overland Park, Kansas, United States

• Expertly executed OCR pipeline operations on documents received from various pharmaceutical and healthcare service provider companies.
• Collaborated closely with the ETL team to ensure smooth and accurate data migration across teams.
• Explored and learnt the latest AWS technologies to provide new capabilities and increase efficiency in the ETL Pipelines.
• Stayed current with the latest AWS technologies and applied them to enhance capabilities and improve efficiency in ETL pipelines.
• Demonstrated expertise in the areas of data management, including integration, modeling, analytics, and reporting by utilizing Python, the AWS ecosystem, and big data tools.

Rockville, Maryland, United States

• Worked for client – Federal Govt. to solve contract document problems with the help of NLP Algorithms both Supervised & Unsupervised.
• Wrote a Flask API Web App which takes one document from client and correctly classifies it with given labels.
• Wrote independent, multiple POC’s for document types to identify / extract specific information from documents using Pytesseract – Tesseract OCR packages in Python.
• Leveraged NLTK, Spacy, Faasttext libraries to perform all kinds of NLP operations including but not limited to cleaning, stemming, lemmatization, word encoding, etc.

Dallas/Fort Worth Area

• Worked for marketing team to deliver actionable insights by leveraging historical data and applying various statistical / machine learning algorithms
• Understood business requirements, tested various hypothesis about underlying mechanics of the business processes and wrote clean, efficient code in R and Python.
• Prepared presentations and reports on findings as well as recommended next steps to ensure successful project completion.

San Francisco Bay Area

• Worked closely with onshore and offshore (Banglore) analytics team to implement multiple use-cases which solely focuses on solving Cisco's enterprise level quality domain problems.
• Implemented numerous classification ( Logistic Regression, Decision Tree, Random Forest Classifier, Support Vector Machine, Xgboost, etc. ) and regression (Linear, Ridge, Lasso, PLS, Random Forest Regressor etc. ).
• Validated existing data models and cross-verified results on statistical terms, such as - Accuracy, Kappa Value, RMSE, ROC, etc.
• Productionalized prototype Machine Learning models written in Python on MapR Servers by building end-to-end cycle.
• Performed data cleaning, worked on imbalanced data, implemented feature ranking, etc. on daily fetched records.
• Read input directly in Jupyter Notebook from MapR Hadoop and wrote output of ML models back to Hadoop.

Master’S Degree, Data Science

● Prepared scripts to ensure proper ETL operations and reporting functions with R programming. ● Cleaned datasets with Excel R and Python..

Bachelor’S Degree, Information Technology

Bachelor'S Degree, Information Technology