Principal Data Scientist, Clinical (U.S. Remote)

Job Description

Act as a strategic collaborator across Medical Affairs and cross-functional teams, helping to translate complex clinical data into actionable insights. Support the development of evidence packages that inform regulatory strategies, publications, and broader business objectives. Contribute to the generation of high-quality, scientifically sound outputs by applying advanced analytical methods, including machine learning where appropriate, to help ensure data integrity and accuracy. With strong statistical acumen and a deep understanding of clinical research, play a key part in supporting data-driven decisions and evidence-based communication. Job duties:

• Partner with Clinical Scientists to perform data exploration, statistical summaries, and visualization to support abstracts, manuscripts, and podium presentations.
• Serve as a bridge between Clinical Science and Biostatistics, translating clinical questions into analytically sound plans.
• Use Python, R, Java, or similar programming languages to conduct exploratory endpoint analyses, identify trends, and support subgroup investigations beyond primary statistical models.
• Apply machine learning techniques (e.g., anomaly detection, clustering, predictive modeling) to identify data integrity issues, inconsistencies, and potential outliers across large clinical datasets.
• Evaluate protocol performance using data-driven approaches to identify deviations, operational inefficiencies, and risk indicators across trials.
• Serve as a thought partner to clinical and medical leadership, providing insight into endpoint behavior, subgroup trends, real-world comparators, and data integrity.
• Generate publication-quality outputs (figures, tables, and supplementary visuals) tailored for conference submissions, peer-reviewed journals, and external presentations.
• Collaborate with Biostatistics and Clinical Operations to ensure that exploratory analyses align with protocol, SAP, and publication goals.
• Partner with Biostatistics to refine statistical analysis plans and interpret outputs through the lens of scientific and clinical relevance.
• Stay current with industry trends and advancements in data science techniques.
• Develop and maintain detailed dashboards and reports (e.g., graphs, charts, tables, etc.) prepared for routine trending, interim data interpretation, senior management reviews, ad-hoc requests, and cross-functional requests as needed.
• Comply with applicable Laws and Regulations, adhere to Quality Management System processes and requirements as well as demonstrate Ethics and Integrity in all matters and at all levels throughout the organization.
• Perform additional duties as assigned.
  
  

Qualifications

• PhD in Data Science, Biostatistics, Epidemiology, Bioinformatics, or a related quantitative field.
• Minimum eight (8) years of relevant data science or industry experience.
• Proven experience in data analysis, statistical modeling, and machine learning techniques.
• Experience in using various platforms and languages such as C, C , Java, JavaScript, Python, R, SQL, MapReduce, Hadoop, Hive, MySQL, etc.
• Strong data wrangling skills with Pandas, tidyverse, or SQL.
• High proficiency with Excel (e.g., pivot tables, lookup tables, graphs, macros, etc.).
• Strong written and verbal communication skills.
• Ability to multitask and work collaboratively.
• Very strong interpersonal skills with the ability to interact positively with all levels of management and communicate problems to appropriate teams within the organization.
• Proficient with MS Office Suite including Word, Outlook, Teams, etc.
  
  

Desired Qualifications

• Experience in developing data visualization with Access, Tableau, or Power BI.
• Familiarity with clinical data standards (SDTM, ADaM, CDASH) and terminology (e.g., mRS, NIHSS, etc.).
  
  

Posting Country

US - United States