Data Scientist II

Responsibilities

• Participates in collaborative data science projects with academic researchers, oncologists, statisticians, and other partners.
• Develops reproducible statistical analyses and machine learning models for topics such as: cohort identification, clinical characterization, and patient-level prediction.
• Thinks critically and communicates clearly throughout the data science lifecycle (problem formulation, data cleaning, EDA, analysis, evaluation, and communication of results).
• Creates data visualizations, reports, queries, and summaries to communicate findings to collaborators.
• Supports development and growth of our common data model (OMOP) for real-world, observational health research through investigating data quality, conducting exploratory analysis on new data sources, and making recommendations for data transformation requirements.
• Identifies, understands and creates multimodal data packages integrating clinical and research laboratory data to create comprehensive descriptions of patient journeys.
• Collaborates with the translational data science team to develop templates, packages, and documentation for the data science community at Fred Hutch and self-serve analytics users.
• Ensures analyses meet a high standard for methodological rigor and stays current in methodology for real-world evidence studies.
• Complies with data governance and data privacy policies.

Qualifications

• B.A., B.S. in computational biology, biostatistics, computer science, data science, biophysics, bioinformatics, or a related field.
• Minimum 5 years of experience in data science, bioinformatics, or related disciplines.
• Graduate degrees can apply towards this minimum (M.A./M.S. = 2 years, PhD = 4+ years).
• Preferred Qualifications: Graduate degree in epidemiology, biostatistics, statistics/mathematics, public health, computational biology, bioinformatics, biology, or a related field.
• Proficiency in R and/or Python programming.
• Strong SQL and experience working in cloud-based data ecosystems.
• Experience working with the OMOP common data model and OHDSI tools.
• Demonstrated knowledge of machine learning and deep learning.
• Demonstrated rigor and reproducibility through well organized and well documented code and/or committed to a public code repository.
• Experience using Git in a collaborative setting.
• Experience working with standardized medical vocabulary and ontologies (ICD-10, SNOMED, RxNorm, etc.).
• Experience with data governance processes for working with regulated data (HIPAA, GDPR, etc.).
• Strong oral and written communication skills, and the ability to prioritize written documentation.
• Excellent interpersonal and communication skills with audiences with a wide range of data expertise.
• A functional understanding of medical oncology, cancer epidemiology, or immunotherapy.
• Proficiency in natural language processing tasks and tools, especially with clinical text.