Job Summary
This new programmer position would be joining the programming team at the Michigan Clinical Outcomes Research and Reporting Program (MCORRP) at Arbor Lakes. Their work will involve artificial intelligence-based data abstraction in the areas of pulmonary embolism and anticoagulation. Dr. Colin Greineder will manage this hires work related to pulmonary embolism while Dr. Geoff Barnes and Brian Haymart will manage this hires work related to anticoagulation. Work location will be hybrid, with the majority of work performed remotely with the exception of occasional mandatory in-person staff or lab meetings.
Mission Statement
Michigan Medicine improves the health of patients, populations and communities through excellence in education, patient care, community service, research and technology development, and through leadership activities in Michigan, nationally and internationally. Our mission is guided by our Strategic Principles and has three critical components; patient care, education and research that together enhance our contribution to society.
Why Join Michigan Medicine?
Michigan Medicine is one of the largest health care complexes in the world and has been the site of many groundbreaking medical and technological advancements since the opening of the U-M Medical School in 1850. Michigan Medicine is comprised of over 30,000 employees and our vision is to attract, inspire, and develop outstanding people in medicine, sciences, and healthcare to become one of the world’s most distinguished academic health systems. In some way, great or small, every person here helps to advance this world-class institution. Work at Michigan Medicine and become a victor for the greater good.
What Benefits can you Look Forward to?
- Excellent medical, dental and vision coverage effective on your very first day
- 2:1 Match on retirement savings
Responsibilities*
The role will involve the design and deployment of natural language processing (NLP) and large language model (LLM) pipelines that abstract quality-of-care metrics from electronic health record (EHR) free text e.g., radiology reports. Amongst the required skills will be blending of classic BERT variants (ClinicalBERT, BioBERT) with LLMs implemented locally and on a high-performance computing cluster with open-source resources. In addition, prompt-engineering and few-shot curation through the U-M GPT Toolkit API will employ larger frontier LLMs. The role will require developing rigorous validation frameworks with scikit-learn and torchmetrics automating precision, recall, F1, AUROC/PR curves, calibration plots, and stratified cross-validation. They will also need to work with staff and students who manually abstract EHR data for model training and validation and other programmers/analysts at MCORRP.
Required Qualifications*
- Masters degree in data science
- 1-2 years of experience
- Experience using Large Language Models to extract text-based information from datasets
- Experience with Python, SQL, C/C++, R, and programming languages
- Experience blending ClinicalBERT and BioBERT variants with large language models on high-performance computer clusters with open-source resources
- Experience developing validation frameworks with scikit-learn and torchmetrics to automate performance curves, calibration plots, and stratified cross-validation.
- Experience translating model outputs into Tableau or Streamlit dashboards to communicate findings
- Knowledge about data privacy and security
Desired Qualifications*
- Experience working with and communicating with students
- Experience working in a clinical research environment and communicating with clinicians and researchers
Work Locations
Work will be remote except for attending monthly in-person staff meetings at Arbor Lakes
Modes of Work
Positions that are eligible for hybrid or mobile/remote work mode are at the discretion of the hiring department. Work agreements are reviewed annually at a minimum and are subject to change at any time, and for any reason, throughout the course of employment. Learn more about the work modes.
Additional Information
This is a term-limited appointment. At the end of the stated term, your appointment will terminate, and will not be eligible for Reduction-in-Force (RIF) benefits. This term-limited appointment does not create a contract or guarantee of employment for any period of time as you will remain subject to disciplinary or other performance measures, up to and including termination, at the will of the University in accordance with existing University policy and standards for employee performance and conduct.
Background Screening
Michigan Medicine conducts background screening and pre-employment drug testing on job candidates upon acceptance of a contingent job offer and may use a third party administrator to conduct background screenings. Background screenings are performed in compliance with the Fair Credit Report Act. Pre-employment drug testing applies to all selected candidates, including new or additional faculty and staff appointments, as well as transfers from other U-M campuses.
Application Deadline
Job openings are posted for a minimum of seven calendar days. The review and selection process may begin as early as the eighth day after posting. This opening may be removed from posting boards and filled anytime after the minimum posting period has ended.
U-M EEO Statement
The University of Michigan is an equal employment opportunity employer.