About this role
Engineer in the Healthcare Research organization working on building a state of the art clinical language understanding system, by creating appropriate corpora. Major duty is to select and distribute data for annotation to internal staff, collect and analyze the annotated data and integrate this into the research pipeline.
Main responsibility is creating and organizing large annotated clinical text corpora for training models for clinical information extraction/understanding.
The candidate will be responsible for the end-to-end research data acquisition process which includes:
Identify data requirements for models and research.
Select the appropriate data from an unannotated large corpus.
Conduct data analysis to identify and correct potential problems.
Distribute the data to annotation staff.
Monitor data annotation consistency during and after annotation phase.
Convert the data to appropriate format for further research.
The candidate will be responsible for creation and maintenance of the data acquisition and validation tools.
Company:
Nuance
Qualifications:
Required Skills:
3-5 years professional development expereince.
Excellent programming skills and at least 2 years of experience programming in Python is required
SQL or other Database knowledge is required
Bash/Unix scripting skills are required.
Must be self-motivated and detail oriented, with exceptional communication and inter-personal skills.
BSCS required. MSCS strongly preferred.
Preferred Skills:
Experience with collecting, creating and maintaining large corpora is a definite PLUS.
Experience with Java or C++ is a definite PLUS.
Experience working with speech recognition, language modeling/processing, machine translation, information extraction etc is a definite PLUS.
Experience in medical text analytics and/or clinical information retrieval is a definite PLUS.
Experience working with UMLS components (MeSH, Specialist etc) and/or SNOMED is a definite PLUS.
Level of experience (years):
Mid Career (2+ years of experience)
How to apply:
Please mention NLP People as a source when applying