About the job Data Scientist I
Role OverviewThe Data Scientist I performs data science and statistical analysis activities under the direction of the Data Scientist II Lead. This role focuses on data processing, statistical modelling, visualization, and clinical data support for NLM's translational science and biomedical informatics efforts.
Key Responsibilities- Perform data collection, cleaning, standardization, imputation, and harmonization.
- Conduct statistical analyses including regression analysis, predictive modelling, and research synthesis.
- Support longitudinal studies using clinical data such as EHR linked with claims data.
- Perform data visualization using standard NLM tools.
- Apply NLP techniques to extract and standardize unstructured clinical text into categorical data.
- Support development and maintenance of systems for storing, searching, analyzing, and viewing clinical data.
- Assist in secure development of information systems that handle PHI/PII incompliance with FISMA.
- Utilize AI/ML techniques including supervised/unsupervised learning and deep
learning for analytical algorithm development. - Document all outputs, reports, and analytical methodologies.
- Support data interoperability tasks across clinical systems.
- Participate in team meetings, sprint planning, and Agile ceremonies.
- Assist in generating status updates and progress reports for management.
Required Skills & Qualifications- Bachelor's or master's degree in data science, Statistics, Biomedical Informatics, or related field.
- Minimum 3-5 years of relevant experience.
- Proficiency in Python, R, and SQL.
- Working knowledge of ML/DL frameworks.
- Experience with clinical datasets, PHI/PII handling requirements, and HIPAA compliance.
- Familiarity with NLP techniques and tools.
- Strong written and oral communication skills.
- Ability to work in an Agile/Scrum environment.
Technologies & Tools- Python, R, SAS, SQL, Spark SQL.
- Tableau, Databricks, Splunk, Google Analytics, PowerBI
- Jupyter Notebooks.
- scikit-learn, TensorFlow or PyTorch (working knowledge).
- AWS, GCP, or Azure (working knowledge) Git/GitHub.
