Digital Health And Behavior Data Scientist

(ID: 2026-1781) Axle is a bioscience and information technology company that offers advancements in translational research, biomedical informatics, and data science applications to research centers and healthcare organizations nationally and abroad. With experts in biomedical science, software engineering, and program management, we focus on developing and applying research tools and techniques to empower decision-making and accelerate research discoveries. We work with some of the top research organizations and facilities in the country including multiple institutes at the National Institutes of Health (NIH). Axle is seeking a Digital Health And Behavior Data Scientist to join our vibrant team at the National Institutes of Health (NIH) supporting the National Institute on Drug Abuse (NIDA) located in Baltimore, MD. Benefits We Offer: 100% Medical, Dental Vision Coverage for Employees Paid Time Off and Paid Holidays 401K match up to 5% Educational Benefits for Career Growth Employee Referral Bonus Flexible Spending Accounts: Healthcare (FSA) Parking Reimbursement Account (PRK) Dependent Care Assistant Program (DCAP) Transportation Reimbursement Account (TRN) Overview: This position will provide advanced computational and data science expertise to support digital health and behavioral research within the NIH Intramural Research Program. This position is responsible for leading multimodal data integration, machine learning and simulation modeling, and supporting human subjects research activities to advance understanding of substance use, treatment outcomes, and recovery. The ideal candidate will demonstrate a strong publication record, including peer-reviewed scientific papers as first author, senior author, or contributing middle author, reflecting substantive contributions to computational modeling, machine learning, AI-driven research, or digital health studies. Certifications Licenses Good Clinical Practice (GCP) Field of Study Computer Science Social Psychology Information Sciences Statistics and Decision Science Software SQL Pytorch TensorFlow Hugging Face Pandas Open AI API Integration AWS, Azure GitHub, Jupyter Notebook RedCap Mobile Sensing Platforms Python MATLAB Linux R Skills Machine Learning Generative AI Natural Language Processing / LLMs Computational Simulation Modeling Multimodal Time-Series Data Analysis Reproducible Data Science (Python/R) Human Subjects Research Support Manuscript writing Ordering Supplies Data Presentation Data Analysis SOP writing Deliverables: Run Validation - Ad-Hoc Meet with lab members to present updates - Ad-Hoc Documented Data Pipelines: Fully documented and reproducible data ingestion, preprocessing, quality control, and feature extraction pipelines for all assigned multimodal datasets. - Ad-Hoc Curated Analytical Datasets: Cleaned, integrated, and analysis-ready datasets with accompanying data dictionaries and processing documentation. - Ad-Hoc Validated Models: Implemented and evaluated machine learning, NLP, and/or generative AI models with documented methodology, performance metrics, validation results, and interpretation of findings. - Ad-Hoc Simulation Models: Developed computational simulation models (e.g., agent-based, predictive, or generative agent models) with written documentation of assumptions, parameterization, calibration, and sensitivity analyses. - Ad-Hoc Reproducible Code Repositories: Version-controlled, well-documented code repositories (with clear README files) sufficient for replication by other researchers. - Ad-Hoc Technical Documentation: Written model documentation describing design decisions, input features, target definitions, modeling tradeoffs, and limitations. - Ad-Hoc Progress Summaries: Written summaries of completed analyses, model performance, dataset updates, and next steps. - Ad-Hoc Manuscript Drafts and Figures: Draft and revised scientific manuscripts, methods and results sections ... (truncated, view full listing at source)