Data Scientist- School of Medicine, Radiology and Imaging Sciences

Emory • Atlanta, GA

1d

About The Position

The Data Scientist in the HITI Lab within Radiology and Imaging Sciences is responsible for building and maintaining large-scale multimodal breast imaging data pipelines, evaluating and validating clinical AI screening models, developing structured data extraction systems using large language models (LLMs), and conducting clinical analytics research for internal and external stakeholders. The position is externally funded through active NIH research grants.

The Data Scientist mines and analyzes information from internal and external data sources to support improvements in operations, clinical outcomes, and business strategies. The role works with organizational stakeholders to develop data-driven solutions, uses large datasets and models to assess possible courses of action with predictive algorithms, and evaluates the effectiveness and accuracy of data sources and collection techniques.

The role requires expertise in at least one programming language, proficiency in statistical theory and mathematical distributions, and experience querying relational databases with SQL. It also involves applying machine learning techniques such as clustering, decision-tree learning, and artificial neural networks.

Requirements

• Master's or PhD in Statistics, Mathematics, Computer Science, or another quantitative field.
• At least 3 years of relevant experience.
• Expertise in at least one programming language, such as R, SAS, or Python.
• Proficiency in statistical theory and underlying mathematical distributions.
• Expertise querying relational databases with SQL.
• Experience with machine learning techniques, such as clustering, decision-tree learning, and artificial neural networks, and the ability to demonstrate real-world application of these techniques.

Nice To Haves

• Master’s degree in Data Science, Applied Statistics, Biomedical Informatics, or a related field.
• At least 2 years of data science experience.
• Experience with clinical and medical imaging data, including DICOM, EHR, and HL7/FHIR.
• Proficiency in Python, R, and SQL.
• Experience with cloud platforms such as GCP or Azure and ML pipelines.

Responsibilities

• Build and maintain large-scale multimodal breast imaging data pipelines.
• Evaluate and validate clinical AI screening models.
• Develop structured data extraction systems using LLMs.
• Conduct clinical analytics research for internal and external stakeholders.
• Mine and analyze data from internal and external sources to support improvements in operations, clinical outcomes, and business strategies.
• Work with stakeholders throughout the organization to develop data-driven solutions.
• Use large datasets, models, and predictive algorithms to test the effectiveness of different courses of action.
• Assess the effectiveness and accuracy of data sources and data-gathering techniques.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level