New Jersey, United States
Founding engineer. Built distributed NLP ML pipelines (Python, Spark, Airflow) that leveraged an on-premise Hadoop cluster to provide businesses with metrics on their โdigital footprintโ and effectiveness of marketing campaigns ๐ฃ
Built a number of solutions to collect data from social media websites using developer APIs, as well as custom web crawlers to collect data from review sites, forums, etc. This data was analyzed by several NLP solutions, then stored in HDFS and visualized via Hive and Power BI. The data was used to train/improve existing ML models. Orchestrated the daily execution of collection, analysis, and Power BI report generation via Apache Airflow. The reports were served to the user in an Angular/Django web app.
Pivoted with business to AI solutions for maritime operations.