Data Scientist
Geo OwlAbout the role
Geo Owl · SDVOSB · Est. 2013
Data Scientist
NGA MAVEN PROGRAM · DATA ARCHITECTURE · GEOINT · EXPERT · KEY POSITION
NGA Maven's AI/ML pipeline runs on a complex, multi-domain data architecture — and keeping it operational, compliant, and scalable takes serious engineering. As the Expert Data Scientist, you'll maintain the data backend that enables preprocessing across security domains and systems: building pipelines, managing databases, enforcing governance, and solving the hard cross-domain problems that most data engineers never encounter.
Role Overview
The Data Scientist supports the maintenance and implementation of the data architecture for all Program data. This position requires experience with databases, cloud architectures, and compliance with data standards, and is responsible for maintaining data backend workflows that allow for data operations across security domains and across systems. You'll build and sustain pipelines, manage database infrastructure, enforce data governance, support cross-domain solutions, and ensure training data remains accessible, accurate, and compliant at scale.
Source-Derived Role Summary
The Data Scientist shall support the maintenance and implementation of the data architecture for all Program data. This position requires experience with databases, cloud architectures, and compliance with data standards. This position is responsible for maintaining data backend workflows that allow for data operations across security domains and across systems.
A Day in the Life
- ✓Build and maintain database tables, schemas, and health alerts for emergent sensor data; set up ETL pipelines to ingest, transform, and load new imagery data in compliance with government schemas and governance requirements
- ✓Develop API-based workflows to enable data movement between platforms across security domains; exhibit proficiency in programming APIs and data version control management
- ✓Monitor data health alerts and pipeline availability; triage issues to ensure training data operations remain optimized and accessible
- ✓Conduct QC on data holdings — validating format compliance (JSON, parquet, XML, CSV), schema adherence, access controls, and metadata standards
- ✓Create and maintain government-directed software and computing environments: government-directed system connections, GitLab repositories, development environments for preprocessing work
- ✓Assess and report data holdings compliance status in written and oral form to government stakeholders
Why This Role Matters
Mission Impact
Without the backend infrastructure you maintain, Maven's model development pipeline stops. The data architecture you build and sustain is what makes it possible to turn overhead imagery into actionable intelligence at scale.
Geo Owl Impact
As a Key Position, your engineering reliability strengthens Geo Owl's standing as a trusted technical partner on Maven and demonstrates the data capability that underpins program performance.
Your Growth
You'll develop rare expertise in cross-domain data engineering within classified government cloud environments — including hands-on experience with NGA enterprise tooling, ATO processes, and government system access credential management.
Core Responsibilities
- ▸Create the necessary infrastructure to store and process data related to emergent sensors: database tables and schemas, data health alerts, and ETL pipelines
- ▸Develop workflows to enable API-based movement of data related to emergent sensors between platforms
- ▸Ensure all emergent sensor data adheres to government-directed data schemas, formats, and governance requirements
- ▸Develop, construct, test, and maintain databases and large-scale, complex data processing systems
- ▸Clean, prepare, and transform data to support geospatial data pipelines that create curated views of content for IC consumption
- ▸Support cross-domain solutions using NGA enterprise tooling; manage the generation, approval, and population of data into databases ensuring security compliance
- ▸Configure and monitor data health alerts to ensure training data operations are optimized and accessible
- ▸Create and maintain government-directed computing environments (version-controlled code repositories and software environments) to enable preprocessing development activities
Apply for this role
Generate a tailored application kit with a matched cover letter, interview prep, and CV highlights — in under 60 seconds.
Apply Now →Generate Application KitFree account required — sign up in 30s