Senior Data Scientist

Geo Owl · SDVOSB · Est. 2013

NGA AGAIM PROGRAM · DATA ARCHITECTURE · GEOINT AI · SENIOR LEVEL · KEY POSITION

The imagery that supports NGA's AI model accreditation program doesn't move itself. It has to be ingested, standardized, transformed, and routed across security domains with precision — and that requires a data engineer who can build the backend that makes it all work. As a Senior Data Scientist on AGAIM, you'll own the data architecture and pipeline infrastructure that enables the accreditation pipeline to run: building ETL workflows, managing database schemas, and solving the cross-domain data problems that stand between an AI model and its accreditation clearance.

As a Senior Data Scientist on the AGAIM program, you support the maintenance and implementation of the data architecture that enables the program to store, process, and move imagery data across security domains and systems. Working alongside imagery scientists and the AGAIM government team, you'll build and sustain the pipelines and database infrastructure needed to ingest emergent sensor data, apply ETL transformations to standardize it for labeling and model testing, and move it between platforms via API. You'll bring deep database and cloud architecture experience, strong programming skills, and the ability to work within classified government IT environments. This is a SCIF-based role performed at a contractor facility.

• ✓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 alignment with government schemas and governance requirements
• ✓Develop API-based workflows to enable data movement between platforms as directed by the government; assess metadata, format, and schema differences when integrating new sensors into the existing data operations pipeline
• ✓Determine pre-processing and standardization approaches for new sensor data — file format conversions, geospatial tiling (chipping), orthorectification, and other data transformations needed for labeling and model testing
• ✓Monitor data health and pipeline availability; address issues that could block imagery delivery to the accreditation testing pipeline
• ✓Ensure all sensor data adheres to government-directed schemas, formats, and governance requirements; maintain documentation and standards compliance throughout the pipeline
• ✓Available during NGA core hours (10am–2pm EST) to coordinate with imagery scientists and the government customer on data architecture and pipeline questions

• ▸Build and maintain database infrastructure (tables, schemas, health alerts, ETL pipelines) to store and process emergent sensor data in support of AGAIM Level 3 accreditation
• ▸Develop API-based workflows to enable data movement between platforms across security domains as directed by the government
• ▸Ensure all sensor data adheres to government-directed data schemas, formats, and governance requirements throughout the pipeline
• ▸Assess metadata, format, and data structure differences for new sensors; adapt ETL processes, schemas, and APIs accordingly to enable clean ingestion into the existing data operations pipeline
• ▸Determine pre-processing and standardization requirements for new sensor data — file format conversion, tiling/chipping to specified geospatial bounds, orthorectification, and other data transformations required for labeling and model testing
• ▸Maintain pipeline reliability and data availability across AGAIM's operational environment; respond to data health issues that could block the accreditation testing workflow

• ✓Active TS/SCI clearance with eligibility for SI/TK/G/HCS/NATO access; CI polygraph required or willingness to obtain
• ✓Minimum 10 experience points required (see experience point calculation below)
• ✓4+ years of experience working with SQL or NoSQL databases and cloud architectures
• ✓Experience leveraging APIs to query systems and migrate data
• ✓Experience with programming languages including Python, JavaScript, or Java
• ✓Experience developing and sustaining operational data pipelines supporting multiple data formats and interfaces
• ✓Excellent written and verbal communication skills; ability to articulate complex technical concepts to both lay and expert audiences

Experience Point Requirement

This is a Senior-level (Level 4) position requiring a minimum of 10 experience points. Points are calculated as follows:

• Education: Associate's = 2 pts  ·  Bachelor's = 3 pts  ·  Master's = +2 pts  ·  PhD = +3 pts
• Professional / Military Experience: 1 pt per year of relevant experience
• Certifications: 0.5 pts each
• Specialized Training: 0.25 pts per relevant course
• Professional Impact (publications, presentations, patents): up to 3 pts total

• ▸You're fluent across the data stack — schema design, API development, ETL orchestration, and cross-domain data movement feel like one integrated problem to you, not separate tracks
• ▸You navigate classified environments with precision — you understand that government system access credentials and ATO requirements, and security domain constraints aren't overhead, they're the architecture
• ▸You can assess a new sensor's metadata and schema against an existing pipeline and tell the team exactly what needs to change before the first data arrives
• ▸You take governance seriously — you understand that non-compliant data in the accreditation pipeline produces unreliable test results, and you prevent it at the ETL layer
• ▸You communicate your engineering decisions clearly — you can explain a schema change or a pipeline failure to imagery scientists and program managers who don't speak SQL

This role builds deep expertise in geospatial data engineering within a classified government environment — including cross-domain data solutions, NGA enterprise tooling, and AI/ML-ready pipeline architecture. Experience maintaining data infrastructure for a government AI accreditation program that spans multiple computer vision programs (multiple NGA AI/ML programs) is a highly differentiated credential for data engineers pursuing senior or architect-level roles in the defense and intelligence community.