Built high-quality data pipelines and optimized data assets of over 500M rows with AWS, Glue, and PySpark

Worked with domain experts/developers to verify fault hypotheses and root cause analyses on highly imbalanced datasets using SKLearn, PyCaret, Pandas, Seaborn, Sagemaker

Developed end-to-end dashboards for 50+ users including data processing of several terabytes to Machine Learning models and visualizing with UX/UI

Produced and deployed scraping cron jobs, a database with its API and a client app

Tech stack: Python, MongoDB, JS/React/Redux

Adapted the app's logic for MongoDB to be ACID

Managed a team together with task priorities

Normalized and analyzed document datasets at scale

Learned AWS services and deployed the software in AWS

Obtained clients for the app, ensured their satisfaction with good maintenance of the product

Managed the whole cloud infrastructure of the company, deployed and maintained client’s websites

Ensured the recruitment process for the upcoming team