Cancer Neuroscience Data Scientist | Hybrid, Impactful

University of Texas MD Anderson Cancer Center; Houston (TX); Hybrid; USD 107,000 - 160,000; Full time

Benefits offered by this job

Referral bonus

Relocation assistance

Job summary

The University of Texas MD Anderson Cancer Center is seeking a data scientist to support the Cancer Neuroscience Program (CNP) by building data infrastructure, analytic workflows, and data-driven tools for cancer neuroscience research.

You will design, implement, and maintain reproducible data pipelines for prospective and retrospective cohorts, enabling secure access and rigorous analytics across enterprise data resources.

Qualifications

• Three years of scientific software or industry development/analysis experience.
• Experience with enterprise data platforms and healthcare data.
• Strong communication with technical and non-technical stakeholders.

Responsibilities

• Create and maintain a structured inventory of neuro-focused datasets and data assets across the institution.
• Document dataset attributes, ownership, access requirements, data dictionaries, and cohort definitions.
• Serve as a technical connector between investigators and enterprise data stakeholders to improve awareness and alignment of data assets.
• Identify opportunities to harmonize, link, reuse, and scale datasets across projects while supporting data governance and interoperability.
• Assist leadership by using data inventories and analytics outputs to inform planning, collaboration, and grant development.
• Design, build, and document data pipelines for prospective and retrospective oncology cohorts.
• Collect, clean, harmonize, preprocess, and validate data from multiple sources for quality and reproducibility.
• Develop and maintain transparent, well-commented codebases for routine and advanced data science tasks.
• Create reusable workflows and documentation to enable efficient data access, analysis, and collaboration.

Skills

Python

R

SQL

Spark

Foundry

Machine learning

Data governance

Education

Bachelor's degree in Biomedical Engineering, Computer Science, Statistics, or related field

Master's or PhD preferred

Tools

Foundry

Microsoft Fabric

AWS

Azure

GCP

Job description

The University of Texas MD Anderson Cancer Center is seeking a data scientist to support the Cancer Neuroscience Program (CNP) by building data infrastructure, analytic workflows, and data-driven tools for cancer neuroscience research.

You will design, implement, and maintain reproducible data pipelines for prospective and retrospective cohorts, enabling secure access and rigorous analytics across enterprise data resources.