Responsibilities include:

• Devised and utilized algorithms and models to mine big data stores, perform data and error analysis to improve models, and clean and validate data for uniformity and accuracy.
• Programmed Robust Data Pipelines utilizing Data science Techniques.
• Implemented ensemble models, convolutional Neural Networks using TensorFlow, Python, and Scikit-Learn.
• Results: Developed a working wheel classification model with an accuracy of 91% on a noisy sensor data.

Responsibilities include:

• Mined 40GB of patent claims text data using Natural Language Processing techniques and Google BigQuery.
• Created a Data Orchestration pipeline in Apache Airflow to rerun queries for 300+ keywords.
• Designed and created Database of Patent keywords in MySQL from extracted information.

Responsibilities include:

• Mined data from primary and secondary sources, then reorganizing said data in a format that can be easily utilized by HIV researchers.
• Provided Valuable insights to researcher’s creating Dashboards and Visualizations using R Shiny
• Prepared reports for Researchers that effectively communicates trends, patterns, and predictions using relevant data. Collaborated with programmers to identify opportunities for process improvements, recommend system modifications