Classification Title:
Assistant Scientist
Job Description:
The Computational Microscopy Imaging Lab (CMI Lab) led by Dr. Pinaki Sarder in the Department of Medicine at the University of Florida is seeking a highly creative and motivated Assistant Scientist to lead in the development and implementation of custom resources and tools.
Under the direction of Dr. Sarder and alongside the CMI Lab Team, the assistant scientist will work on applying and implementing cutting-edge techniques in data science towards the development of software solutions using spatial omics and microscopy imaging data to study the cellular and molecular microenvironment in tissues from diverse organ systems. The assistant scientist will manage primary data, derived data, annotations, and modelling and data processing as well as integrate spatial omics and microscopy data in a user-friendly web visualization interface, and ensure that the user experience and user interfaces of our tools meet the needs of a diverse group of stakeholders. Work will include the detection, segmentation, and quantification of micro and macro anatomical structures in tissues, predictive modeling of diseases, as well as image and molecular omics data fusion and scalable data visualization, while ensuring accurate quality control and assurance of data as well as data standardization and maintaining best practices for software development. The work may involve conducting user experience surveys of the developed visualization tool.
The successful candidate should have a background in computation, data science, and machine learning. Strong graphic design skills and experience in creating visual identities will be a plus. The candidate will write progress reports, contribute to research manuscripts, and attend conference meetings. The successful candidate will have access to many opportunities for collaborative research at one of the leading and most vibrant medical schools in the country and contribute to a diverse and inclusive environment through their scholarship, mentoring, and professional service.
The Assistant Scientist will do the following:
- Supervise research support staff, including OPS staff, graduate students, and post-doctoral associates, across multiple projects.
- Apply and implement cutting-edge data science tools for various medical imaging analysis problems.
- Adhering to biomedical and patient ontologies and controlled vocabularies, define data quality metrics and data standardization, and establish processes to measure, maintain, and monitor metrics continuously, ensuring team compliance with established quality standards.
- Develop data collection workflows to extract metadata from source files, convert pixel data into appropriate file format container, load extracted metadata into file format container, and add post-conversion information in file format container flags.
- Develop and utilize instruments and methods for the evaluation and quality control of data, such as ensuring that image artifacts have been identified.
- Utilize primary data, derived data, and annotations to produce transforms of data and models for summarizing, analyzing, predicting, simulating, reasoning, generating hypotheses, and testing hypotheses.
- Map existing experimental and data processing pipelines into a framework that can be captured by existing workflow languages (CWL and Model Cards).
- Encode and store modeling and data processing pipelines to derived data or annotation standards, as appropriate. Store and tag derived data with metadata by experiment.
- Responsible for selecting and applying appropriate analytical methods to answer questions and test hypotheses as specified by clinicians and end users. This will require expertise in database design, data ontology practice, and statistical analyses.
- Provide data management solutions to projects that use programming ranging from simple scripting (PowerShell, JavaScript) through full stack development including database design, middleware/services layer implementation, and HTML/JavaScript/TypeScript-based user interfaces.
- Ensuring data quality throughout all stages of acquisition and processing, including data sourcing/collection, ground truth generation, and computer vision.
- Work with CMI Lab leadership and stakeholders to define and establish data quality definitions and rules consistent with CMI Lab priorities in support of a consistent ontology.
- Manage communications related to data quality and work with data owners and partners to prevent and remediate identified quality issues using both manual and automated solutions.
- Interact with a range of experts in machine learning and other advanced analytic processes.
- Collect, analyze, interpret, and summarize data in preparation for generation of statistical and analytical reports. Utilize statistical software to analyze and interpret research data.
- Develop databases for collection, tracking, and reporting of data.
- Independently develop, complete, and maintain analyses and reports using inferential statistical measures. Interpret results of these analyses and provide explanations for variances in measures used for software development recommendations.
- Collaborate with IT staff on improvements to or development of data infrastructure.
- Collaborate with end users and lab team to understand user needs; propose designs of software to meet these needs.
- Design, build, and test solutions using standard technologies and tools to meet established needs based on expert understanding of the structures and resources necessary to resolve stakeholder requests.
- Develop reporting mechanisms via dashboards.
- Assist with business intelligence needs, validating visualizations, and concept development.
- Responsible for data analysis, dissemination, and archiving of metrics for the CMI Lab reports and improvement of software development.
- Participate in compiling reports of analyses to stakeholders and sponsors, proposal writing, and manuscript writing.
Expected Salary:
$90,000; commensurate with experience & education
Minimum Requirements:
PhD in computer science, computer engineering, information systems, or related field.
Necessary Qualifications
- Demonstrated experience with medical data management and familiarity with health care information and patient data.
- High-level experience with software development.
- Knowledge and experience with software development practices (Agile & DevOps)
- Familiarity with Fast Healthcare Interoperative Resources (FHIR), microscopy whole-slide imaging, DICOM, the Open Microscopy Environment, and REDCap.
- Strong knowledge of SWL, NoSQL, and other database systems and data storage solutions.
- Knowledge of CWL and Knowledge Cards.
- Experience managing large-scale databases and data repositories.
- In-depth knowledge of general data science/programing languages and frameworks, such as Python, Java, and Node.js.
- Understanding of RESTful API design and experience in creating and implementing APIs.
- Knowledge of data management best practices, data governance, data modeling, and data warehousing.
- Experience with data integration and business intelligence software (SAP product stack).
- Experience with data visualization and reporting tools such as Tableau and Power BI.
- Experience with general statistical software (e.g. SAS, R).
- Experience working with cloud structures (AWS, Azure, Google Cloud).
- Experience with API management tools and platforms such as Apigee, Kong, or AWS API Gateway.
- Experience with containerization (Docker, Singularity, Kubernetes, etc.).
- Experience working with high-performance computing clusters (HPCCs).
- Experience with version control systems (VCS; e.g., Git).
- Knowledge of security and privacy considerations in data management and data handling.
- Ability to plan, organize and coordinate work assignments.
- Ability to work effectively and independently.
Preferred Qualifications:
- Design and deployment of real-world, large-scale, user-facing systems is preferred.
- Track record of academic research and/or scientific publications
- Excellent technical writing and communication skills.
Special Instructions to Applicants:
In order to be considered, you must upload your resume.
Application must be submitted by 11:55 p.m. (ET) of the posting end date.
Health Assessment Required:
Yes
Advertised: 20 Sep 2023 Eastern Daylight Time
Applications close: 12 Oct 2023 Eastern Daylight Time