A

Andrew Philpot

About

Detail

Senior Data and Software Engineer | NLP, AI, Big Data
South Pasadena, California, United States

Timeline

work
Job
school
Education
folder
Project

Résumé

Jobs verified_user 0% verified
  • Two Six Technologies
    AI MIL Data Pipeline Engineer
    Two Six Technologies
    Oct 2025 - Current (1 year 1 month)
  • Age of Learning
    Data Scientist, Data Engineer
    Age of Learning
    Jan 2016 - Oct 2025 (9 years 10 months)
  • University of Southern California
    Research Scientist
    University of Southern California
    Jul 1995 - Dec 2016 (21 years 6 months)
    Software design, development in Big Data + relational data, natural language processing, information integration, Semantic Web, social media
  • NASA Ames Research Center
    Research Programmer
    NASA Ames Research Center
    Aug 1990 - Jul 1995 (5 years)
    Research programmer for planning and automated software engineering applications
  • Texas Instruments
    Software Design Engineer
    Texas Instruments
    May 1986 - Aug 1988 (2 years 4 months)
    On Pilot's Associate development: suite of on-aircraft expert systems for mission planning, system status assessment
Education verified_user 0% verified
  • Stanford University
    MS, Computer Science
    Stanford University
    Jan 1988 - Dec 1990 (3 years)
  • Duke University
    Bachelor of Science (B.S, Mechanical Engineering
    Duke University
    Jan 1983 - Dec 1986 (4 years)
  • North Carolina School of Science and Mathematics
    North Carolina School of Science and Mathematics
    North Carolina School of Science and Mathematics
    Jan 1980 - Dec 1982 (3 years)
Projects (professional or personal) verified_user 0% verified
  • K
    Karma: A Data Integration Tool
    Jul 2014 - Current (12 years 4 months)
    Karma is a tool to semi-automatically integrate data from a variety of sources. Karma's unique capability is that it learns semantic descriptions of the sources, which map the contents of a source (e.g., all the columns in a spreadsheet) to a domain ontology that the user specifies. Karma uses these descriptions to integrate data from multiple sources, merging fields only when their meaning is the same, and publishing the integrated data in a variety of formats, including graph databases and NoSQL stores. The key features of Karma are (1) flexibility, because the users can define the domain models that are appropriate for their application and Karma can map many different types of sources (relational, spreadsheet, CSV, XML, JSON and Web API
This is a community-created genome.