Homeoffice Data Scientist Manager, Molecular Diagnostics Programs chez Ultragenyx pharmaceutical
Ultragenyx pharmaceutical · United States - Remote, Estados Unidos Da América · Remote
Exponent – Réussis tes entretiens tech avec des simulations et des coachs experts issus des meilleures entreprises.
Sponsorisé par ExponentPosition Summary:
ultrafocused – Work together to fearlessly uncover new possibilities
The Molecular Diagnostic Programs (MDP) Data Scientist Manager is a creative and innovative team member within Global Medical Affairs. The MDP Manager partners internally and externally to develop locus-specific databases and diagnostic program reporting tools, with a focus on integrating Machine Learning (ML) and Natural Language Processing (NLP) techniques to enhance data extraction and analysis. The MDP manager delivers dashboards reporting on molecular diagnostic program data for scientific business purposes. The MDP manager collaborates internally with bioinformatics, medical affairs (including HEOR/Epidemiology, Patient Diagnosis Programs, and MedInfo), and other business functions to create data science-based resources. Proficiency in data visualization and user experience (UX) design are essential for developing quality MDP resources for enduring internal and external use. A portfolio demonstrating experience in data analysis, AI/ML/NLP applications, and UX design implementation is highly encouraged.
Work Model:
Remote: Officially documented as working full-time from home, with travel to Ultragenyx's offices or other locations on occasion as needed.
Responsibilities:
- Develop locus-specific databases by analyzing complex datasets with internal/external partners for interactive feedback including development, curation, harmonization and maintenance.
- Ensure compliance with data integrity standards and best practices for database maintenance.
- Prepare data and design/technical requirements for the database website to engineering team.
- Build strong cross-functional relationships with medical affairs, clinical, and business teams to deliver data science-based reports and solutions that align with organizational goals.
- Design, document, and manage interactive data dashboards, including parameter-specific views, dimensional drill-down capabilities, and ad hoc analysis for deeper insights.
- Leverage expertise in dashboard design principles, best practices, data quality, and performance optimization to provide recommendations for visualization, implementation, testing, and production readiness.
- Develop and implement NLP and ML models to extract disease-related information from biomedical literature, clinical notes, and structured/unstructured data sources.
- Create algorithms and workflows to integrate extracted data into databases and dashboards, using generative ML/AI techniques to automate standardization, ensuring consistency and accuracy.
- Create documentation for best practices, maintenance, and user training to ensure long-term usability and scalability of data science-based tools.
- Stay up to date with advancements in data science, ML/AI, NLP, and biomedical informatics to enhance data extraction, harmonization, and analysis techniques.
Requirements:
- Master’s degree or equivalent preferred in Health Informatics/ Bioinformatics/ Data Science/ Computational Biology or equivalent.
- Bachelor’s degree (required) in Biology, Computer Science, Mathematics, Information Systems or related field.
- 3+ years of experience with Python and proficiency with MongoDB and R.
- Experience with PowerBI, Tableau or similar visualization tools for dashboard creation and reporting.
- Experience with one or more of: JavaScript, Django, Shiny, D3.js, HTML.
- Expertise in NLP, ML, and AI-driven text extraction techniques applied to biomedical literature and clinical datasets.
- Experience with containerization technologies, particularly Docker, for deploying and managing applications.
- Experience working with Electronic Health Record (EHR) data, including familiarity with ICD-10 and CPT code ontologies, as well as phenotyping ontologies.
- Experience developing and maintaining locus-specific or biomedical databases, including curation and harmonization protocols.
- Familiar with molecular genetic diagnostic testing results reporting and working knowledge of HGVS nomenclature.
- Strong analytical skills with the ability to perform data investigations (e.g., source identification, data joins, assessing data quality) and experience in statistical analysis and methodologies.
- Excellent problem-solving, organizational, and communication skills, with the ability to work in a fast-paced, deadline-driven environment.
- Ability to work independently while managing competing priorities & projects.
- Able to build strong cross-functional relationships and strong oral and written communication skills.
Ultragenyx Pharmaceutical is an equal opportunity employer and prohibits unlawful discrimination based on race, color, religion, gender, sexual orientation, gender identity/expression, national origin/ancestry, age, disability, marital and veteran status, and any other status or classification protected by applicable federal, state, and/or local laws. Reasonable accommodation will be provided for all protected statuses or classifications protected by applicable law, including individuals with disabilities, disabled veterans, for pregnancy, childbirth, and related medical conditions, and based on sincerely held religious beliefs. Applicants can request an accommodation prior to accepting a job offer. If you require reasonable accommodation in completing this application, or in any part of the recruitment process, you may contact Talent Acquisition by emailing us at talentacquisition@ultragenyx.com.
