1240 Malvern Avenue
Pittsburgh, PA 15217
A software engineering and scientific leader and manager. Focus on
implementing data mining and machine learning systems that solve real
business problems. Expert in statistical and linguistic methods for
data mining, information extraction and classification. Skilled
communicator and leader.
Engineering Manager, January 2006 - current Google, Pittsburgh, PA
Charter member of Google Pittsburgh, responsible in part for selecting
and initiating high-impact projects, recruiting and growing the office
from two to eighty, and establishing and building out local
facilities. Directly manage a team of twenty leading projects in ads
selection, product search and improving the user experience on other
Google search properties using applied data mining, machine learning
and information extraction techniques.
Director of Applied Research, July 2003 - January 2006 Research Scientist, July 2002 - July 2003 Intelliseek, Inc., Pittsburgh, PA
Head of Intelliseek's Applied Research Center. Led a group of
scientists and engineers in developing a large-scale system that
analyzes internet text content for market research analysis. Emphasis
on creating and using leading-edge data mining, machine learning, and
linguistic algorithms. Responsible for directing the software
development, product development, and research agenda of the
company. Performed targeted research in the areas of text
classification and sentiment analysis, resulting in patent
applications and publications.
Research Scientist, June 2001 - May 2002 WhizBang! Labs, Pittsburgh, PA
Applied state-of-the-art machine learning algorithms to business
applications on the web. Created a job title extractor that reduced
site loss by 50% for Flipdog.com using Maximum Entropy Markov
Models. Created a web-based market research application for generating
sales leads from corporate data extracted from the web. Invented and
implemented text classifiers for automatically placing job postings
into a hierarchy. Consistently met deliverable deadlines at or beyond
specified performance criteria.
Graduate Research Assistant, August 1996 - May 2001 Carnegie Mellon University, Pittsburgh, PA
Created algorithms and systems for text and hypertext classification
and extraction. Coauthored eighteen refereed publications. Performed
research in statistical text learning, learning with unlabeled data,
and relational text learning. Built a web-crawling agent that extracts
information from the web into a propositional knowledge base. Teaching
assistant for an introductory data structures and algorithms course
and an artificial intelligence course. Summer internships at Justsystem Pittsburgh Research Center and WhizBang! Labs.
Software Engineer, December 1995 - August 1996 Virtual Office, New York, NY
Designed and developed software in a start-up setting. Led projects on
server-side web-tracking software, forms-based web page generation,
and third-party, sharable certificate management.
Database Applications Engineer, July 1994 - October 1995 Oracle Corporation, Redwood Shores, CA
Designed and developed database applications for Oracle Financial
Applications. Heavy emphasis on database design, graphical user
interfaces, performance tuning, and quality assurance. Project leader
for a new accounting module that tracks foreign currency transfers
between corporate subsidiaries.
Visiting Lecturer, Carnegie Mellon University, Fall 2007
Organized and co-taught Internet Search
Technologies, 15-505, a special topics seminar class at CMU
targeted to advanced undergraduate and early graduate students. The
class teaches large-scale distributed computation, information
retrieval, machine learning for text and hypertext, and UI design.
Teaching Assistant, Carnegie Mellon University, Fall 1999
Teaching assistant for introductory computer science class,
Fundamental Structures of Computer Science I, 15-211.
Teaching Assistant, Carnegie Mellon University, Fall 1997
Teaching assistant for undergraduate artificial intelligence class,
Fundamentals of Artificial Intelligence, 15-381.
Laboratory Teaching Assistant, Massachusetts Institute of Technology, Spring 1992
Laboratory teaching assistant for introductory computer science class,
Structure and Interpretation of Computer Programs, 6.001.
Ph.D. Computer Science, Carnegie Mellon University, 2001 M.S. Computer Science, Carnegie Mellon University, 1999
Ph.D. Thesis: Using Unlabeled Data for Text Classification, Advisor: Tom Mitchell
Thesis research on methods for integrating unlabeled data into supervised learning in text and hypertext domains. Other research in text classification, information extraction, data mining, and clustering.
S.B. Mathematics with Computer Science
S.B. Cognitive Science
Massachusetts Institute of Technology, 1994
GPA: 4.9/5.0; Phi Beta Kappa; Sigma Xi (science research); National Merit Scholar.
Research with Susan Carey on human mechanisms for face recognition.
KDD-2008 and KDD-2007 Student Travel Awards chair
Co-coordinator CMU Machine Learning Department/Google Seminar Series
Area chair for NIPS 2006
Member, University of Pittsburgh Department of Computer Science Industry Board
Program Committee member for ICML, KDD, SIGIR, WWWC, AAAI, COLING, ACL, PAKDD, ICWSM, etc., and a number of workshops
Journal Reviewing for Machine Learning, Journal of Machine Learning Research, Computational Linguistics, ACM TOIS, Applied Intelligence, etc.
Invited AI Seminar talk at ISI/USC, March 2007
Lecturer at 2006 Machine Learning Autumn School at CMU's Machine Learning department
Co-organizer for IJCAI '01 Workshop on Text Learning: Beyond Supervision
Niels Provos, Yunkai Zhou, Clayton W. Bavor, Jr., Eric Davis,
Mark Palatucci, Kamal P. Nigam, Christopher K. Monson, Panayiotis
Mavrommatis, Rachel Nakauchi. Intrusive Software Management. Filed October 5, 2007. Pending.
Kamal Nigam and Matthew Hurst. Topical sentiments in
electronically stored communications. Filed September 30, 2005.
Kamal Nigam and Robert Stockton. Method for developing a
classifier for classifying communications. Filed March 16, 2004.