Data Scientist Cancer Neuroscience

UT MD Anderson Cancer Center•Houston, TX

1d•Onsite

About The Position

The Cancer Neuroscience Program (CNP) Data Scientist role will serve as a key technical and analytical resource supporting the development, implementation, and maintenance of research data infrastructure, analytical workflows, and data-driven tools for the CNP. As an institutional signature priority, CNP brings together multidisciplinary efforts focused on the intersection of cancer, the nervous system, brain health, and neuro-oncology. Reporting to the Director, Research Planning & Development, this position will support prospective and retrospective oncology cohorts; design and maintain transparent, reproducible, and auditable data pipelines; enable data access and workflow development in platforms such as Foundry and related institutional data environments; perform exploratory and advanced analytics; develop predictive and prescriptive models; and translate complex data into actionable insights for scientific, operational, and strategic decision-making. The role will also help create and maintain visibility across neuro-focused datasets, cohorts, and data assets across the institution, serving as a technical connector between CNP-supported investigators, institutional research data resources, the Institute for Data Science in Oncology, the institutional Research Data Office, and other enterprise data stakeholders. This function is intended to improve awareness, responsible access, reuse, harmonization, and strategic alignment of data assets relevant to cancer neuroscience research. The ideal candidate is a technically strong, research-oriented data scientist who can operate effectively in a matrixed academic healthcare environment, communicate clearly with technical and non-technical stakeholders, and contribute directly to cancer neuroscience research, publications, reporting, and long-range program planning. The candidate should be intellectually curious, service-oriented, highly organized, and capable of supporting multiple concurrent projects in a fast-moving, multidisciplinary research environment.

Requirements

Bachelor's Degree Biomedical Engineering, Electrical Engineering, Computer Engineering, Physics, Applied Mathematics, Science, Engineering, Computer Science, Statistics, Computational Biology, or related field.
Three years scientific software or industry development/analysis experience.
With Master's degree, one year required experience.
With PhD, no experience required.

Nice To Haves

Master’s degree or PhD in Science, Engineering, Data Science, Computer Science, Statistics, Biomedical Informatics, Computational Biology, Bioinformatics, Biostatistics, Public Health, or related field.
Experience in academic healthcare, oncology, cancer research, clinical research, translational research, or biomedical research.
Experience working with EPIC-derived clinical data, electronic health record data, prospective or retrospective cohorts, clinical registries, institutional research datasets, real-world clinical data, or multimodal biomedical datasets.
Experience with Foundry or similar enterprise data platforms.
Experience developing analytical workflows, dashboards, technical reports, reusable data products, or data pipelines for research or operational stakeholders.
Experience contributing to peer-reviewed publications, abstracts, grant applications, scientific presentations, philanthropy reports, or institutional strategy documents.
Experience with machine learning, natural language processing, large language model-enabled workflows, or AI applications in healthcare or research settings.
Experience working collaboratively with clinicians, scientists, statisticians, bioinformaticians, data engineers, research staff, and institutional data teams.

Responsibilities

Create and maintain a structured, current inventory of neuro-focused datasets, cohorts, registries, biospecimen-linked datasets, clinical data assets, imaging datasets, patient-reported outcomes, molecular datasets, and other relevant research resources across the institution.
Document key attributes of institutional data assets, including dataset ownership, access requirements, data dictionaries, cohort definitions, refresh cadence, data limitations, analytical readiness, and potential research use cases.
Serve as a technical connector between CNP-supported investigators, neuro-focused research initiatives, institutional data teams, the Institute for Data Science in Oncology, the institutional Research Data Office, and other enterprise data stakeholders to improve awareness, responsible use, and strategic alignment of data assets.
Identify opportunities to harmonize, link, reuse, and scale existing datasets across CNP-aligned projects while reducing duplicative data collection and supporting institutional standards for data governance, documentation, and interoperability.
Support CNP leadership in using data asset inventories and analytical outputs to inform project prioritization, infrastructure planning, collaboration opportunities, grant development, philanthropy reporting, and long-range strategic planning.
Design, build, maintain, and document data pipelines supporting prospective and retrospective oncology cohorts, including clinical, research, operational, and multimodal datasets.
Collect, clean, harmonize, preprocess, and validate data from multiple sources to ensure accuracy, completeness, usability, and reproducibility.
Develop and maintain transparent, auditable, and well-commented code bases for routine and advanced data science tasks.
Create reusable workflows, templates, and documentation that enable efficient data access, analysis, reporting, and collaboration across CNP-supported projects.
Work with large datasets using coding languages, analytical tools, and data platforms such as Python, R, SQL, Spark, Foundry, Microsoft Fabric, AWS, Azure, GCP, or comparable environments.
Perform exploratory data analysis to identify trends, patterns, anomalies, missingness, bias, and potential signals relevant to cancer neuroscience research.
Develop, test, validate, and refine predictive and prescriptive models using statistical methods, machine learning, artificial intelligence, and other advanced analytical techniques.
Design and implement analytical experiments to validate hypotheses, evaluate model performance, and support scientific decision-making.
Provide onboarding, hands-on training, and technical support to research staff and project teams using Foundry and related institutional data platforms, including best practices for data access, workflow development, documentation, and collaboration.
Assist users in defining analytical questions, resolving technical issues, improving workflows, and translating research needs into feasible data science approaches.
Collaborate with clinicians, laboratory scientists, data scientists, data engineers, statisticians, bioinformaticians, research staff, and program leadership to optimize data insights and support CNP-aligned research priorities.
Communicate findings effectively through visualizations, dashboards, reports, presentations, and clear written summaries tailored to technical and non-technical audiences.
Collaborate on scientific publications, abstracts, grant applications, technical reports, and other documentation for use by faculty, leadership, advisory boards, philanthropy, and project teams.
Prepare technical reports and other documentation for use by upper management and team members for short- and long-range projects and planning.
Contribute to institutional data integration efforts by helping align CNP-specific data needs with broader IDSO-supported platforms, standards, and analytical capabilities.
Ensure data governance, privacy, security, documentation, and compliance standards are followed in all data science activities.
Stay current with emerging tools and techniques in data science, machine learning, artificial intelligence, clinical informatics, and big data technologies.
Other duties as assigned.