Data Scientist2018 - PRESENTIndependent
Technologies: Python, Scikit-learn, Pandas, Carrot2, Spark, Whoosh, Elasticsearch
- Built a data cleansing and normalization pipeline for a Fortune 500 company's entire eCommerce catalog using Pandas and Spark.
- Built an equivalent product matcher for 2 global regions using Whoosh.
- Built customer feedback topic clusters for executive action using Pandas and Carrot2.
- Built an SEO category landing page tagger using product metadata.
- Built a product taxonomy classifier for products with missing taxonomy tags using Scikit-learn, Pandas, and Solr.
Principal Consultant2008 - 2015Microsoft Corporation
Technologies: Enterprise Search, SharePoint, C#, Powershell, SQL Server
- Architected global enterprise search deployments for major corporations using SharePoint and FAST.
- Led relevance tuning and conducted customer education workshops.
- Developed the FAST ImPulse eCommerce search engine.
- Served as the team lead on many enterprise search deployments.
- Helped a customer build an innovative chemical search by drawing chemicals.
Architect2003 - 2008FAST Search
Technologies: FAST, Python, C#, PHP
- Architected many enterprise search deployments.
- Assisted with development, product management, analysis, deployment and support for FAST Impulse eCommerce search engine.