Lead Machine Learning Analyst-bioinformatic
Employment Type: Full-Time
The Division of Pediatric Gastroenterology, Hepatology and Nutrition at Cincinnati Children's hospital is seeking a highly motivated Data Scientist. The successful candidate will be able to apply their machine learning knowledge to unique health and biological data, with opportunities to collaborate beyond the institute. The position will report directly to Dr Dhaliwal (Assistant Professor in the GI Division) and will interact closely with the biomedical informatics division. The appointment will entail additionally a secondary appointment in the division of biomedical informatics. The candidate must be comfortable working as part of a team, and requires effective communication with colleagues of various backgrounds, skill sets, and educational experience. The multi-disciplinary nature of the program affords great opportunity for a candidate's growth and development.
Here's What You'll Get To Do:
* Apply state-of-the-art machine learning methods to clinical and molecular data
* Contribute to cutting-edge findings in biology and health
* Develop data processing and reporting pipelines to manage and maintain data quality and provenance
* Work in a casual work environment where learning and development are keys to success
May manage reporting personnel; making decisions regarding; and taking responsibility for recruitment; selection; on-boarding; development; training; discipline; termination; evaluation; salary; payroll; and/or retention. May maintain and/or create position descriptions and/or performance evaluation criteria.
Leads data curation/management efforts across multiple projects. Curates, annotates and organizes various types of biomedical data (e.g., genomic, clinical, imaging, sequencing) in various formats (e.g., flat files, relational and non-relational databases). Leads the design and implementation of metadata management solutions. Leads the design and implementation of secure data storage solutions including within cloud environments. Leads the design and implementation of data characterization/quality assessment routines of moderate to advanced complexity including development and application of domain-specific metadata standards. Leads the design and implementation of annotation and query/discovery solutions.
* Data Analysis
Leads the development of robust pipelines for curating, processing and analyzing biomedical data of various types (e.g., genomic, clinical, imaging, sequencing). Utilizes/configures existing software and leads the development of new tools to support complex data management tasks (e.g., sequence alignment, variant calling, inter-sample comparison, patient matching/linkage). Designs and develops scalable, searchable and secure data structures, utilizing and expanding standards as much as possible. Incorporates multi-institutional resources and 3rd party software into specialized analysis workflows for the team and project. Leads the development and maintenance of computational infrastructures to control the flow of data and information for studies. Provides web-based bioinformatics tools and access to public and proprietary relational databases. Documents standard operating procedures based on best practice. Works in collaboration with both technology and scientific teams.
* Requirements Gathering & Analysis
Interfaces with clinicians/researchers to collect and analyze requirements including highly complex workflows. Leads problem-solving and solution evaluation/design efforts. Leads the analysis of current environments and ensures alignment of solutions with user workflows and institutional and industry standards.
* Software Evaluation & Development
Leads the evaluation and development of software solutions to support moderate to complex data workflows. Documents requirements, defines scope, objectives, and priorities, and formulates systems to parallel overall strategies. Formulates and defines systems scope and objectives through research and fact-finding combined with an understanding of applicable systems and industry requirements. Provides leadership and direction for software development life cycle, including identification of key stakeholders, design requirements gathering, system analysis and design, task prioritization, code generation, testing and implementation. Develops detailed implementation plans and manages to completion. Effectively communicates the status of all efforts to necessary parties. Utilizes project and time management skills to complete projects within specific timeframes.
Develops and executes data analysis plans. Generates reports for publications. Contributes significant content to scientific publications and participates in scientific meetings. Works closely with biostatistics department on the production of publication and presentation materials.
* Masters degree in related field. May require clinical license, certification or training
* 5 - 7 years of work experience in a related job discipline.