Job DescriptionResearch Associate Data Scientist (Cedars-Sinai Medical Center; Los Angeles, CA): Assist with the development, evaluation, and application of computational and statistical methods, including artificial intelligence and machine learning algorithms and software for the analysis of biomedical data. Assist with the presentation and communication of scientific results through laboratory meetings, scientific conferences, and peer-reviewed publications. Create database-to-deployment pipelines for models using the necessary programming languages (primarily Python, R, and C++). Create sustainable data science infrastructure and adheres to data analysis/machine learning best practices. Perform exploratory data analysis to gauge the need for or appropriateness of advanced analytical methods. Work with senior or lead data scientists, research programmers, and principal investigators to identify areas where data science can best be applied to answer biomedical research questions. Test and validate code to ensure robustness of data applications. Perform all other duties as assigned. Participate in the development of innovative algorithms and analytical methods. Participate in the evaluation and interpretation of all analytical methods and results. Participate in the oral and written communication of scientific results including publications.
Minimum requirements: Master's degree or foreign equivalent in Electrical Engineering, Computer Science, Machine Learning, Applied Mathematics, Biomedical Imaging, or related field, plus three (3) years of experience as a Research Associate Data Scientist, Computer Engineer, Biomedical Data Scientist, or related occupation.
Must have experience with the following: Python, C++, and R; developing, testing, validating, and optimizing production-level, version-controlled code (GitHub/GitLab and Azure DevOps) for algorithm development, statistical analysis, and deployment; implementing supervised and unsupervised learning algorithms (random forests, support vector machines, clustering, deep learning), with hands-on expertise training, fine-tuning, and deploying deep learning models using frameworks (PyTorch and TensorFlow), and adapting these methods to biomedical research problems; building end-to-end database-to-deployment pipelines including querying large relational databases (SQL), data cleaning, model training, validation, and deploying models in multiple computing environments; communicating scientific results effectively through peer-reviewed publications, patents, conference presentations, and internal technical reports; working with medical imaging data, including familiarity with industry-standard imaging formats (DICOM), image preprocessing workflows (segmentation, denoising, registration, resampling, and normalization), and use of imaging software libraries (SimpleITK, MONAI, or NiBabel) to prepare data for machine learning analysis; managing, processing, and optimizing large-scale 3D and 4D time-series datasets for deep learning model development on High-Performance Computing (HPC) or cloud-based GPU clusters.
Salary: $97,510 - $133,100 per year
To Apply: Any interested applicant may click on the APPLY NOW button above to apply for this position.
Job Req ID:18558
Responsibilities- Assists with the development, evaluation, and/or application of computational and statistical methods including artificial intelligence and machine learning algorithms and software for the analysis of biomedical data.
- Assists with the presentation and communication of scientific results through laboratory meetings, scientific conferences, and peer-reviewed publications.
- Creates database-to-deployment pipelines for models using the necessary programming languages (primarily R, Python, SQL, neo4j).
- Creates sustainable data science infrastructure and adheres to data analysis/machine learning best practices.
- Performs data cleaning, quality control, and exploratory data analysis to gauge the need for or appropriateness of advanced analytical methods
- Assists research, senior research, and/or lead research data scientists and principal investigators to identify areas where data science can best be applied to answer biomedical research questions.
- Tests and validates code to ensure robustness of data applications with version control through GitHub.
