Received from Philip Ogren, 1 June 2006

We have a job opening for an analyst/programmer in the field of Biomedical Natural Language Processing. Below is a rough outline of the kind of candidate we are looking for. For more information about the position, the Mayo Clinic, in Rochester, MN, you are encouraged to visit us online at The posting is #9928.


This position will support software development efforts for natural language processing research and the Mayo Clinic Life Sciences Text Project. Primary responsibilities include: annotator design, development, and testing with a focus on algorithm development, application, and evaluation.

Department: Biomedical Informatics

Qualifications: Bachelor of Science degree in Computer Science, Linguistics, Applied Math or related field. Graduate degree in one of these fields with 3+ years of software development experience is preferred. A combination of education and experience may be considered. Candidates should have significant background in one of these areas: Machine Learning (ML) or Natural Language Processing (NLP). A candidate with ML background should understand general principles of supervised and unsupervised machine learning and have a working knowledge of several of the basic ML algorithms. Experience with applying ML techniques to NLP problems is desirable. A candidate with NLP background should have a general understanding of basic NLP challenges such as document retrieval, named entity identification, and information extraction and approaches for evaluating systems that perform these tasks. Experience working with NLP modules such as tokenizers, parsers, and POS taggers is required. Experience in software development using an object oriented programming language is required with preference given to Java/J2EE technologies. Experience with parsing, generating, and transforming XML is required. Familiarity with UNIX operating systems is desirable. Must be willing to work and assimilate into a team environment and also possess the skills to work independently. Must possess excellent analytical, problem-solving, and technical design skills. Strong oral and written communication and interpersonal skills are required.

This is a full-time position with normal working hours Monday through Friday. Isolated overtime and participation in 24x7 on-call rotation is expected. Candidate must be willing to remain in this position for a minimum of two years.

Additional Experience and/or Qualifications: The preferred candidate will have a Masters or Doctoral degree in advanced fields of computer science, computational linguistics, or math. Familiarity with biomedical vocabularies and classification systems is desirable. In addition to the required skills experience, familiarity in the following environments and technologies is preferred: GATE, UIMA, Weka, SQL, UML, and Perl.