Extensive experience in large scale text/data mining, machine learning, map/reduce(hadoop), search engine(lucene), scientific computing, matrix computation Specialties:Java, C/C++, shell script, perl, mysql, postgreSql, matlab, data mining, machine learning, scientific computing, hadoop, lucene, weka, mallet

Software Engineer @ From June 2015 to Present (5 months) Greater New York City AreaSenior Software Engineer @ 9. GTM realtime Reporter (data storage for time series, ingests > 250,000 records/second) 8. New generation of Realtime Data Analysis System (hadoop, hbase, time series) 7. Report export module(ppt, pdf) for the new Portal website 6. Server side Highcharts generator 5. Data Layer for the new Portal website 4. Data replication module for Realtime Data Analysis System 3. Optimized the data store of Realtime Data Analysis System 2. Rewrote search engine for internal report website 1. Data Import Module for internal report website 0. 2012 B.A.A. Half Marathon -1. 2013 Baystate Marathon From October 2010 to June 2015 (4 years 9 months) Boston, MAModeling Engineer @ Worked on the research and development of large scale behavioral targeting advertisement algorithm using map/reduce(Hadoop). 5. Bagged/Boosted Decision Tree for cookie scoring 4. Maximal correlation for cookie scoring 3. Feature selection and redundency removal from milllions of features 2. Model analysis using feature segment 1. Daily traffic data pipeline management 0. Active foosball, pool, shuffle ball and pingpong player From February 2010 to October 2010 (9 months) Software Engineer @ Worked on the backend of this popular job search engine: 6. Chinese word segmentation 5. Canadian job categoriation(based on NOC, English and French version. Term analysis, document correlation) 4. Language recognization 3. US job categorization(based on Onet. Term analysis, document correlation) 2. Web bot detection from Apache weblog 1. Arima model for revenue prediction From March 2009 to February 2010 (1 year) Data Programming Consultant @ 2. Worked on the natural language processing program to Control Blood Pressure: Reliability and Validity Study; 1. Hidden Markov Model approach for Medical Document Classification From February 2009 to March 2009 (2 months) Summer Intern @ SNAP (Sensor Network for Aging in Place) project. 3. Built the real-time system (Sensor Networks for Aging in Place) for human activity recognition by a wearable 3-axial accelerometer 2. Developed a small Java wavelet transform package and incorporated it in our project 1. Proposed and developed multiple self-calibrated classifiers (self-calibrated Naïve Bayes, Decision Tree, HHM etc.) From May 2008 to August 2008 (4 months) Summer Intern @ Worked on a progress note categorization system, developed our own classifier library, including Decision Tree, SVM and RKHS(reproducing kernel hibert space) based classifier. Meanwhile, improved the performance of the classifiers given the feedback of Medical Scientist. It was a good time working with my supervisor -- Dr.Douglas Roblin. From May 2007 to August 2007 (4 months)

Master, Computer Science @ Georgia Institute of Technology From 2006 to 2008 Master, Scientific Computing @ Peking University From 2002 to 2005 Bachelor, Applied Mathematics @ Zhejiang University From 1998 to 2002 Min Zhang is skilled in: Hadoop, Machine Learning, Data Mining, Java, Perl, Shell Scripting, Matlab, MySQL, Lucene, PostgreSQL, Weka, Scientific Computing, Distributed Systems, Python, Algorithms, Spring, Hibernate, Natural Language..., MapReduce, Scalability, HBase, Programming, Software Engineering, Ruby, Apache