CALIBRE Systems, Inc., an employee-owned management consulting and digital transformation company, is looking for a LEAD DATA SCIENTIST to support our client at the National Institutes of Health (NIH), National Center for Biotechnology Information (NCBI) in Bethesda, MD. NCBI is part of the National Library of Medicine (NLM) whose wide range of applications serve more users and more data than any other US Government Agency. NCBI provides free access to petabytes of biomedical and genomic information with scientists all over the world using NCBI products, including PubMed, ClinicalTrials.gov, GenBank, RefSeq, and ClinVar.

We are seeking a Lead Data Scientist who will work with a team of scientists to develop novel computational methods and software tools for analyzing unstructured text data in the biomedical literature and electronic medical records, to accelerate knowledge discovery and improve healthcare. This position will also be responsible for improving existing text-mining processes and will collaborate with scientists at NLM, the National Institutes of Health (NIH), and outside the NIH on various text mining projects.

 Principal responsibilities include the following:

• Developing and implementing deep learning/machine learning approaches to solve biomedical/biomedicine text mining problems
• Analyzing the unstructured data in biomedical texts to identify various kinds of information required by users and the gaps in the current system
• Writing manuscripts of the proposed methods and demonstration for journal or conference papers

Required Skills Required Experience

• A master’s degree or equivalent in biomedical informatics, computer science, or a closely related field is required (PhD’s degree is strongly preferred)
• Training experience with a strong emphasis on computation and familiarity with NLP & statistical methods in text and data mining, and machine learning
• Deep knowledge of NLP text mining especially information extraction from biomedical text
• Familiar with deep learning methods (CNN, RNN, BERT models, etc.)
• Experience working with named entity recognition, relation extraction, information retrieval, knowledge discovery, and/or other relevant text mining research topics
• Familiarity with biomedical and life science information (e.g., PubMed and PubMed Central)
• Good project management skills and experience
• Excellent communication and presentation skills

 Other Information:

• This position will begin with working remotely until it has been determined by the NIH that workers can return to the NIH campus. Any telework thereafter will be reviewed on a case-by-case basis.
• Position contingent on obtaining an NIH Public Trust and NIH badging.
• Vaccination Status: All CALIBRE employees also agree to follow any additional health and safety mitigation policies that may be required at the workplace.