Data Scientist
University of Chicago
Summary
The Data Scientist will lead data science research efforts within breast cancer program in the Section of Hematology/Oncology in the Department of Medicine.
Job description
Responsibilities
- Manage the program’s projects.
- Develop frameworks for housing multi-modal clinical data – including genomic, pathology, and radiographic imaging data.
- Develop and code data dictionaries for discrete data.
- Write, Implement, and develop efficient code and machine learning tools and pipelines for data processing and analysis.
- Work with collaborators to implement emerging external computational tools for program data.
- Draft grant proposals.
- Develop training material.
- Keep lab's knowledge-based trainings up to date.
- Supervise trainees.
- Perform reproducible genomic data analysis.
- Calibrates data between large and complex research and administrative datasets.
- Guides and may set the operational protocols for collecting and analyzing information from the University's various internal data systems as well as from external sources.
- Designs and evaluates statistical models and reproducible data processing pipelines using expertise of best practices in machine learning and statistical inference.
- Provides expertise for high level or complex data-related requests and engages other IT resources as needed.
- Analyzes moderately complex data sets for the purpose of extracting and purposefully using applicable information.
- Provides professional support to staff or faculty members in defining the project and applying principals of data science in manipulation, statistical applications, programming, analysis and modeling.
- Performs other related work as needed.
Minimum Qualifications
Education: Minimum requirements include a college or university degree in related field. Work Experience: Minimum requirements include knowledge and skills developed through 2-5 years of work experience in a related job discipline.
Preferred Qualifications
Education: Advanced degree in computer science. Experience: Experience in python including torch and scikit-learn libraries strongly preferred. Experience in working with image data or unstructured text data with large language models.
Preferred Competencies
- Proficiency in Linux/Ubuntu OS including basic file and user management, ssh.
- Familiarity with tmux, SLURM.
- Strong Analytical skills.
- Problem-solving skills.
- Organizational skills.
- Verbal and written communication skills.
- Ability to work independently and as part of a team.
Requirements
- College or university degree in related field
- 2-5 years of work experience in a related job discipline
- Advanced degree in computer science (preferred)
- Experience in python including torch and scikit-learn libraries (preferred)
- Experience in working with image data or unstructured text data with large language models (preferred)
- Proficiency in Linux/Ubuntu OS including basic file and user management, ssh (preferred)
- Familiarity with tmux, SLURM (preferred)
- Strong Analytical skills
- Problem-solving skills
- Organizational skills
- Verbal and written communication skills
- Ability to work independently and as part of a team
Benefits
- Health
- Retirement
- Paid Time Off
Company overview
The University of Chicago is a world-renowned private research university founded in 1890 and located in Chicago's Hyde Park neighborhood. As a premier academic institution, it operates one of the most comprehensive biomedical research enterprises in the United States through its Biological Sciences Division, which includes over 1,100 faculty members across 10 basic science and 14 clinical departments. The university manages extensive research infrastructure including the University of Chicago Medicine Comprehensive Cancer Center, multiple specialized research institutes, and maintains affiliations with Argonne National Laboratory and Fermi National Accelerator Laboratory. With research funding exceeding $450 million annually and more than 3,300 patents filed since 1987, the institution is a global leader in scientific discovery and innovation. The Biological Sciences Division alone supports over 500 research-active faculty who secure an average of $588,000 in NIH funding per principal investigator, focusing on areas including cancer biology, immunology, microbiology, molecular metabolism, neuroscience, and evolutionary biology. The university's commitment to interdisciplinary research and its unique position as manager of national laboratories creates unparalleled opportunities for translational research and scientific advancement.