Data Scientist, Senior

What Impact You'll Have

GRVTY is hiring a Senior Data Scientist to support an IC program developing an enterprise-scale analytics and data management framework for geospatial intelligence products. The program is in active development - this is not a maintenance role. You will be contributing to a system being built from the ground up, with real influence over how the components are designed and implemented.

The core of the work is applying machine learning, statistical analysis, and data mining techniques to large-scale geospatial and imagery datasets in order to generate automated IV&V metrics and analytical insights. You will work closely with software developers, systems architects, and government stakeholders to design the analytical workflows, build the pipelines that execute them, and ensure the outputs are technically sound and mission-relevant. This role requires someone who is equally comfortable writing production-quality code and explaining analytical methodology to a non-technical government customer.

What You'll be Owning

• Develop and apply machine learning, statistical, and data mining techniques to extract metrics and insights from large-scale geospatial and imagery datasets.
• Design and implement automated analytical workflows that support IV&V evaluation of GEOINT data products across multiple source types and collection geometries.
• Build and optimize data pipelines for ingesting, transforming, and processing multi-source geospatial data at scale.
• Work with software engineers and the solutions architect to integrate analytical components into the broader system architecture - your models need to run in production, not just notebooks.
• Evaluate analytical output quality, identify failure modes, and iterate on methodology to improve metric accuracy and reliability.
• Collaborate directly with government stakeholders to understand mission requirements, validate that analytical outputs are operationally meaningful, and communicate findings clearly.
• Document analytical methodologies, model assumptions, validation approaches, and limitations to a standard that supports program continuity and government review.
• Contribute to trade studies and capability assessments as the program expands into new data types and evaluation scenarios across option years.

What You Must Have

• Active Top Secret clearance with ability to obtain SCI and CI Polygraph.
• Bachelor's degree in Data Science, Computer Science, Mathematics, Statistics, or a closely related quantitative field. Equivalent experience will be considered.
• 9+ years of professional experience in data science, machine learning, or applied analytics, with a track record of delivering production-quality work on real programs.
• Strong Python programming skills, including experience with scientific computing libraries such as NumPy, pandas, scikit-learn, and SciPy.
• Experience building and deploying end-to-end analytical pipelines - not just exploratory analysis, but workflows that run reliably in operational or near-operational environments.
• Experience working with large, complex, or multi-source datasets, including data quality assessment and remediation.
• Ability to communicate analytical methods and results clearly to both technical teammates and non-technical government customers.
• Comfortable working in a structured program environment with formal deliverables, government oversight, and documentation requirements.

What Would be Nice to Have

• Experience with geospatial data, imagery products, or remote sensing datasets - familiarity with the data types matters here.
• Prior work supporting NGA, NRO, or other IC programs, particularly in an analytical or data science capacity.
• Experience with geospatial Python libraries such as GeoPandas, Shapely, Rasterio, or GDAL.
• Familiarity with NGA data systems, GEOINT product formats, or IC data standards.
• Experience deploying analytical workloads in classified or air-gapped IC environments.
• Background in automated quality assessment, data validation, or IV&V methodologies.
• Experience with graph-based or network analytics methods applied to complex, multi-source datasets.
• Familiarity with ML/Ops practices - reproducible training pipelines, model versioning, experiment tracking.
• Advanced degree in a quantitative field.