Senior Data Scientist

Built Python and PySpark pipelines over large structured and unstructured datasets, processing over 100M records per month to support predictive modeling and data asset evaluation. Developed machine learning models in scikit-learn and TensorFlow for ranking and forecasting use cases, improving model lift by 18%. Prototyped deep learning workflows with PyTorch and Keras, designed feature extraction and retrieval logic with Hive, HBase, and Amazon S3, and reduced pipeline runtime by 40%.

Built predictive models in Python and scikit-learn for marketplace demand and customer segmentation. Analyzed mobile and web event data with pandas, SQL, and PySpark, improved conversion by 12%, and designed data structures in Hive and MongoDB for faster retrieval. Ran experiments on online marketing analytics and scaled batch processing on Hadoop and Spark clusters.

Built Python and SQL analysis workflows for clinical and operational datasets. Applied scikit-learn for classification and regression models, improving forecast accuracy by 14%. Queried and reshaped large tables in PostgreSQL, Hive, and Cassandra, and created reproducible notebooks and model evaluation summaries.