| ChoiceMaker Technologies has developed a patent-pending machine-learning system, ChoiceMaker 2.0, that matches records of people, businesses, or other entities in large databases filled with inconsistent information. For instance, ChoiceMaker 2.0 can recognize that “Arnold Schwarzenegger” and “Arnie Shwarzeneger” are the same individual. The system can be used to remove duplicate records from a single database, match records across multiple databases, or search a database approximately. Clients include the New York City Department of Health and the U.S. Census Bureau.
Founded in 1998, ChoiceMaker Technologies is a New York City-based start-up with a highly talented staff that includes three computer science Ph.D.'s. The company has won two Small Business Innovation Research grants from the National Science Foundation totaling $600,000 to further its ground-breaking work in machine learning approaches to approximate record matching.
ChoiceMaker seeks a talented computer scientist, skilled in Java, to perform multiple tasks:
- Customize ChoiceMaker 2.0 for clients, especially to deploy the ML matching system on new data and new types of data.
- Perform NSF-funded research into machine learning, data parsing, and data standardization techniques that will improve ChoiceMaker 2.0’s accuracy or convenience.
- Program Java applications, such as user interfaces and data analysis programs, that expand ChoiceMaker 2.0’s functionality.
Compensation includes a competitive salary, options and an excellent benefits package.
Mandatory Qualifications
1. Deep expertise in object-oriented development, development of thousands of lines of Java
2. Machine learning, computational linguistics/natural language processing (NLP), data mining, or data quality
3. MS or PhD in Computer Science or equivalent experience
Desired Qualifications
1. Record matching, data de-duplication, data cleaning
2. Artificial intelligence (AI). Particularly experimental work involving large datasets.
3. Server side Java: J2EE, CORBA, COM, Web services
4. Java GUI: Swing, AWT
5. Database: JDBC, SQL, Oracle, MS SQL Server, MySQL
6. XML: SAX, DOM, JDOM, XML Schemas
7. Multithreaded Java
8. Various: ant, log4j, JUnit, JavaDoc, Collections
9. Design patterns
10. UML
11. compiler construction
12. project management
13. C++
14. Windows, Linux, UNIX
15. Eclipse plugin development
|
