DATA SCIENTIST II

We are seeking a Machine Learning and Natural Language Processing Data Scientist to contribute to cutting-edge research in the field of health informatics with a focus in pre-trained clinical language models, computable phenotypes in healthcare, health outcomes research, applied machine learning using electronic health record data, and high-throughput information extraction. Join a unique lab of physician-scientists, clinical informatics experts, statisticians, engineers, and computer scientists to innovate and develop models that are closely linked to healthcare practice with opportunities to implement your work into real-time with the goal of bedside clinical decision support. The Data Scientist will work within the UW Critical Care Medicine (ICU) Data Science Lab and across our collaborating sites, whose research focuses on using electronic health record data to improve the care of hospitalized patients.
The ideal candidate will be responsible for the development and build high-impact machine learning and natural language processing models. The individual will use computational methods for preprocessing and feature engineering data from the electronic health record. We are looking for a candidate who could fill a clinical Natural Language Processing subspecialty in our lab.
The staff member will be responsible for providing data for abstract and manuscript submissions and should have prior experience in hosting data challenges/hackathons. They will also assist with the development of abstracts, posters, presentations, and manuscripts and will be involved in project monitoring and evaluation, data analysis, oversight of trainees, and dissemination of program results. This individual will work in close collaboration with the data management team.
SMPH is committed to being a diverse, equitable, inclusive and anti-racist workplace and is an Equal Employment Opportunity, Affirmative Action employer. Applications from Black, Indigenous and People of Color (BIPOC) individuals, LGBTQ+ and non-binary identities, women, persons with disabilities, military service members and veterans are strongly encouraged.

• 10% Prepares data sets for analysis including cleaning/quality assurance, transformations, restructuring, and integration of multiple data sources
• 40% Independently identifies and implements appropriate data science techniques to find data patterns and answer research questions chosen by the lead researcher including data visualization, statistical analysis, machine learning, and data mining
• 15% Organizes and automates project steps for data preparation and analysis
• 10% Composes and assembles reproducible workflows and reports to clearly articulate patterns to researchers and/or administrators
• 5% Documents approaches to address research questions and contributes to the establishment of reproducible research methodologies and analysis workflows
• 15% Development of natural language processing pipelines
• 5% Writing of scientific reports, summarizing studies, and presentation of research

Diversity is a source of strength, creativity, and innovation for UW-Madison. We value the contributions of each person and respect the profound ways their identity, culture, background, experience, status, abilities, and opinion enrich the university community. We commit ourselves to the pursuit of excellence in teaching, research, outreach, and diversity as inextricably linked goals.
The University of Wisconsin-Madison fulfills its public mission by creating a welcoming and inclusive community for people from every background – people who as students, faculty, and staff serve Wisconsin and the world.
For more information on diversity and inclusion on campus, please visit: Diversity and Inclusion

Preferred
Master’s Degree in computer science/engineering, information science, computational linguistics or statistics

Required:
– Three or more years of experience with building neural networks in Natural Language Processing using both PyTorch and Tensorflow.
– Three or more years of experience data wrangling unstructured electronic health record data.
– Experience presenting healthcare data.
– Experience in healthcare research; ability to plan and carry out research experiments and projects in the clinical arena.
– Experience in the field area of clinical natural language processing.
– Experience with medical knowledge sources such as the Unified Medical Language Systems (UMLS), and NLP engines including the Apache clinical Text and Knowledge Extraction System (cTAKES)
Preferred:
– Four or more years of experience of working in a team-based, clinical research environment.
– Previous experience working with electronic health record datasets.
– Previous experience with HIPAA-compliant cloud computing (e.g., AWS, Azure, GCP).
– Previous grant writing experience; manuscript writing; program management and/or development experience.
– Experience contributing to clinical research projects.
– Outstanding communication across all members of the team in order to facilitate strong professional connection and understand/translate data management and analysis needs to all members of the team.

Full or Part Time: 80% – 100%
This position may require some work to be performed in-person, onsite, at a designated campus work location. Some work may be performed remotely, at an offsite, non-campus work location.

Ongoing/Renewable

Minimum $75,000 ANNUAL (12 months)
Depending on Qualifications

Required:
– Experience organizing and managing large datasets in the Electronic Health Record.
– Proficiency in Java, Python, and R
– Proficiency in using PyCharm and Tensorflow
– Proficiency in cloud computing, Databricks, Apache cTAKES, and distributed workflows
– Excellent time management skills and ability to work independently required
– Strong analytical skills required
– Strong familiarity with medical and scientific terminology, including medical vocabularies and ontologies (i.e., CUI, SNOMED, LOINC, MESH, RxNORM)
– Proficiency in the National Library of Medicine Unified Medical Language System Knowledge Sources
– Experience in clinical predictive analytics (both diagnostic and prognostic) and performing biostatistical analyses for descriptive statistics of large medical datasets

To apply for this position, please click on the “Apply Now” button. You will be asked to upload a resume and cover letter as a part of the application process. Please ensure that the resume and cover letter address how you meet the minimum/preferred qualifications for the position. You will also be asked to provide three professional/supervisor references during the application process. References will not be contacted without prior notice.

Kassie Hefty
kjhefty@medicine.wisc.edu
608-262-8538
Relay Access (WTRS): 7-1-1. See RELAY_SERVICE for further information.

Data Scientist II(RE021)

A534285-MEDICAL SCHOOL/MEDICINE/PULMON MED

Academic Staff-Renewable

267918-AS