IR Engineer at Spock Networks
San Francisco Bay Area
IR Engineer at Spock Networks
San Francisco Bay Area
Research revolved around statistical modeling for information retrieval and fault detection. Industry experience in large scale data mining and information retrieval (both from a modeling and architecture standpoint).
Machine Learning, Statistics, Information Retrieval, Network Services, Search/Index Architecture
(Privately Held; 11-50 employees; Internet industry)
February 2007 — Present (1 year 9 months)
Frontend search services:
- autocomplete
- search aggregation
- spellchecker
Backend data-mining projects include mining web references, crawling/indexing, conflation, mining architecture.
Technologies: Python, Perl, C, MySQL, SQL, Xapian, threads, OOP, regex, amazon web services (S3, EC2, SimpleDB)
(Public Company; IBM; Information Technology and Services industry)
May 2006 — December 2006 (8 months)
Significantly improved core Content Protection technology using methods from statistical machine learning.
Developed extensible Bayesian Network Toolkit (Java)
(Educational Institution; Higher Education industry)
September 2004 — December 2006 (2 years 4 months)
TA'd graduate algorithms course (maintained office hours, graded homework & tests)
Research centered on methods from machine learning as applied to:
- software verification
- image segmentation
- personalized document ranking models
- information extraction using tree alignment models