Our clinical research effort employs novel analytic techniques, especially deep learning and machine learning techniques, to identify complex patterns of medical data derived from various sources - both collected through routine clinical care and expressly collected for research purposes. Related to this goal, the Computational and Data Science Research Specialist will lead all facets of managing, cleaning, and analyzing large-scale medical data using machine-learning predominant analytic techniques. The Data Scientist will be involved in developing robust interoperable software pipelines, mostly using Python, for all steps of the process. Data extraction pipelines will need to be developed de novo to obtain data from various clinical systems or sources. Strong familiarity with deep learning and all deep learning frameworks is required, including with native Tensorflow and PyTorch. Prior experience applying and building new deep learning architectures for medical applications is strongly preferred, with demonstrable examples of having done so for other prior domains or examples. Ideally, this prior experience may include using various types of medical data, though experience in other domains is acceptable. Demonstrated ability to adapt existing neural network architectures from other fields is required. Demonstrated ability to build new neural network architectures to suit medical applications is required. Greater than one year of demonstrated real-world experience with the above described neural network-based tasks is required. Uses computational, computer science, data science, and CI software research and development principles, with relevant domain science knowledge, along with professional programming concepts for medium-sized projects or portions of larger projects. Develops and optimizes a variety of computational, data science, and CI research tools and components. Performs research on current and future HPC, data, and CI technologies, hardware, and software projects. Works on algorithm development, optimization, programming, performance analysis, and/or benchmarking assignments of moderate scope where the tasks involve knowledge of either domain/computer science research requirements and/or CI design/implementation requirements. Demonstrated experience in other critical aspects of applying clinical/medical/scientific data to machine learning pipelines is required, such as extracting and cleaning medical/clinical data and storing the data in file systems appropriate for scalability and post-hoc data manipulation. Experience with databases or the ability to learn will be requisite. Under the supervision of the PI, the Data Scientist will also be involved in data analysis and will be fluent in comparing a variety of techniques, including machine learning and deep learning techniques, to be able to empirically determine which approach is most suitable for the given research hypothesis and data type. The ability to learn and implement new techniques depending on the problem at hand will be an essential skill, thus requiring a strong foundation in Python and competency to bootstrap novel algorithmic implementations as needs arise. This position may also include some administrative duties and will have the opportunity to participate in and lead research and authorship teams. Department Description The Department of Medicine is the largest department in the UCSF School of Medicine. To advance health, the Department of Medicine develops and supports innovators in patient-centered care, scientific discovery, medical education, and public policy across five main sites (Mission Bay, Parnassus, ZSFG, VAMC, and Mt. Zion) and 39 divisions. The Division of Cardiology is one of the largest clinical, research, and training divisions of the Department of Medicine (DOM) at UCSF. Within the Division are sub-specialty sections for Adult Congenital Heart Disease; Advanced Heart Failure, Transplant, and Pulmonary Hypertension; Cardiac Electrophysiology; Echocardiography and Cardiac Imaging; General Cardiology, Interventional Cardiology; and Prevention. The Division runs several clinical practices in multiple sites, conducts basic and clinical research via large clinical, Federal, and privately supported research programs and six faculty laboratories, and educates medical students, residents, clinical fellows, and postdoctoral scholars through ACGME as well as non-ACGME training programs. The Tison lab is also part of the Bakar Computational Health Sciences Institute and the Data Scientist will be part of the larger computational community and infrastructure. Required Qualifications Bachelor's degree in Computer / Computational / Data Science, or Domain Sciences with computer / computational / data specialization or equivalent experience. Advanced knowledge of Data science/machine learning / deep learning / HPC Demonstrated advanced knowledge of Python and Pytorch and Tensorflow and other standard data science frameworks a
Location: San Francisco, CA
Posted: Aug. 9, 2024, 5:06 a.m.
Apply Now Company Website