CV
Basics
Name | Amgad Madkour |
Label | Principal Data Science Manager at Microsoft AI |
Url | https://amgadmadkour.com |
Summary | My current work focuses on building large-scale data products that use various artificial intelligence techniques to deliver value to users. |
Work
-
2019.01 - Present Redmond, USA
Principal Data Science Manager
Microsoft
- Autos Marketplace: Technical lead for Automotive Q&A, My Garage, Autos Listings, and Autos AI features that deliver differentiating content to automotive users.
- Platform for Interactive Concept Learning: Maintained and enhanced the model used by Microsoft Edge for extracting product information form e-Commerce domains.
- Entity Matching: Enhanced the performance of the entity matching stack by addressing the highly skewed data issues, delta entity matching, and optimizing the blocking technique.
-
2018.05 - 2018.08 Redmond, USA
Data Scientist Intern
Microsoft
- Conflation Updates: Designed and implemented a conflation update component that is responsible for speeding up the reflection of conflation changes into the Satori final graph.
-
2015.05 - 2015.08 Redmond, USA
Research Intern
Microsoft Research
- Dependency parsing: Conducted a series of experiments ranging from Up-training to Entity Linking to improve the dependency parsing accuracy.
-
2011.05 - 2011.08 Sunnyvale, USA
Research Intern
Yahoo!
- Recommendation system: Developed a recommendation system for local businesses.
-
2006.01 - 2010.07 Cairo, Egypt
Research Engineer
IBM
- Tag Recommendation Technique: Co-Invented and patented a k-partite graph technique for recommendation of tags during bookmarking of resources.
- Spam Detection: Proposed a set of features that identify spamming bookmarks in social media and evaluated their feasibility over various machine learning algorithms.
- Extracting relations from biomedical text: Developed a system that automatically extracts interactions between entities such as proteins, chemicals, and diseases from biomedical text with preliminary focus on protein-protein interactions.
- Machine Assisted Translation: Developed a system that provides suggestions when translating documents. The system uses a continuous space language models for statistical machine translation.
- Unstructured Information Management Platform: Participated in a joint development with Watson lab in Yorktown to develop a system that analyzes large volumes of unstructured textual information from the news domain to discover, organize, and deliver relevant knowledge to end-users.
Volunteer
-
2014.04 - 2015.07 Cairo, Egypt
Education
-
West Lafayette, USA
Awards
- 2006.11.01
Languages
Arabic | |
Native speaker |
English | |
Fluent |