Staff Research Associate III (Data Scientist)
NCIRE - The Northern California Institute for Research and Education, Inc.
Summary
We are seeking a highly motivated and skilled Data Scientist to join our team focused on understanding the complicated relationship between biomechanical markers and aortic disease. This role will be instrumental in leveraging big data approaches to analyze vast datasets, identify patterns, and develop predictive models.
Job description
Essential Functions
Data Acquisition and Processing
- Collaborate with biomechanics researchers and engineers to collect and integrate large-scale biomechanical datasets.
- Develop efficient data cleaning and preprocessing pipelines to handle diverse data types and ensure data integrity.
Feature Engineering and Model Development
- Extract meaningful measures from biomechanical data, potentially including motion capture, force plate, and physiological measurements.
- Design and implement advanced machine learning models (e.g., deep learning, statistical modeling) to predict aortic disease risk progression.
Model Evaluation and Validation
- Develop rigorous evaluation metrics and perform robust statistical analysis to assess model performance.
- Validate model predictions against clinical outcomes and validate findings across diverse patient populations.
Data Visualization and Communication
- Create clear and concise visualizations to communicate complex data relationships and model insights to stakeholders.
- Present findings to research teams, clinicians, and collaborators in a clear and impactful manner.
Collaboration and Research
- Collaborate effectively with researchers, engineers, and clinicians across disciplines to ensure alignment of data analysis with research goals.
- Contribute to publications, presentations, and grant proposals related to the project.
Requirements
- Master's or PhD degree in Computer Science, Data Science, Statistics, Biostatistics, Biomechanics, or a related field.
- 3+ years of experience in data analysis, machine learning, or biostatistics.
- Strong foundation in statistical modeling, machine learning techniques (e.g., classification, regression, clustering), and data mining.
- Proficiency in programming languages like Python, R, or similar, with experience in data manipulation libraries like pandas, NumPy, Scikit-learn, and TensorFlow/PyTorch.
- Experience with big data technologies (e.g., Hadoop, Spark, cloud computing platforms) is a plus.
- Excellent understanding of biomechanics principles, particularly related to cardiovascular health, is preferred.
- Strong communication, visualization, and presentation skills with the ability to convey technical information effectively to diverse audiences.
Company overview
NCIRE - The Northern California Institute for Research and Education, Inc. is the leading private nonprofit research institute in the United States exclusively dedicated to advancing Veterans' health research. Founded in 1988 and operating as a 501(c)(3) nonprofit organization, NCIRE partners with the San Francisco VA Health Care System (SFVAHCS) and the University of California San Francisco (UCSF) to conduct groundbreaking biomedical research. The institute supports over 200 MD and PhD principal investigators working across diverse research areas including Alzheimer's disease, cancer, cardiovascular disease, mental health, post-traumatic stress disorder (PTSD), traumatic brain injury (TBI), and substance use disorders. With $70 million in research expenditures, NCIRE manages the largest funded research program within the Veterans Health Administration, operating from 250,000-300,000 square feet of research space on the SFVAHCS campus. The organization's mission focuses on improving health outcomes for Veterans and active military personnel through innovative scientific discoveries, clinical trials, and translational research that bridges laboratory findings to clinical applications.