o Grew from Developer to Owner of a premium offering, wearing many hats, ensuring a total of 5+ smooth releases.

o Built a Chaos/Soak Testing framework, laying foundation to the company wide Performance, Scalability and Reliability Initiative.

o Implemented business impacting features like lazy loading and automatic pagination improving the performance 10-fold.

o Advocated for and strictly adhered to test driven development and proper documentation to ensure smooth releases.

o Decreased the feature backlog by 50 % in a span of few months, ensuring utmost quality using test-driven development.

Verdigris is an artificial intelligence (AI)-enabled energy management platform for commercial facilities. My role at Verdigris is to work at the intersection of AI and Insights team to help bring Machine Learning algorithms into production.

o Reduced time and effort taken for development by creating a cross-team framework using Spark and Docker to access data.

o Unblocked the creation of auto labeling (critical for the company) by creating interactive device labeling dashboard.

o Pushed towards test-driven development by creating and improving existing tests, catching more bugs before release.

o Created accuracy metrics and automated plotting to help evaluate Verdigris’s energy forecasting algorithm.

o Converted ML algorithms like Classification, Forecasting, Disaggregation into products by developing backend pipelines.

o Developed CI/CD pipelines using CircleCI and Docker to build, test and deploy code to AWS Batch, ECS and Lambda.

o Customized an existing BI tool using Javascript to enable faster development, serving the needs of the fast-paced start-up.

o Developed interactive charts using Highcharts, to showcase various Machine Learning products increasing their value.

CYR3CON is a cyber-threat intelligence platform that scours deep/dark web for information. My role at CYR3CON was to create and improve data pipeline jobs to better manage data scraped from various websites.

o Created data pipeline jobs and improved the execution speed of existing ones by 40% by using Apache Spark.

o Deployed Machine learning models to production and used batch processing to speed up the jobs.

o Created pipeline jobs that queries Elasticsearch, Neo4j, MongoDB to collectively store data.

o Reduced the number of records going into the database from thousands to hundreds by grouping the records.

o Visualized data from Elasticsearch using Kibana, queried Neo4j, created MongoDB collections as per requirements.

o Designed end to end AWS based solution for acquiring twitter account data and built classification models.

o Improved the accuracy of tweet classification by 10% and Twitter account classification by 5%.

o Created SQL database, created ORM for Python-SQL, created and used restful endpoints using python flask.

o Performed supervised learning, improved data modeling, and feature extraction, dealt with large datasets.

o Trained and tested various machine learning models, deployed models on AWS EC2, stored data on AWS S3.