Exploitation Specialist/Data Steward

Select Search Associates LLC; Arlington (VA); On-site; USD 130,000 - 170,000; Full time

Job summary

Select Search Associates LLC in Arlington, VA seeks an experienced Explotation Specialist/Data Steward to design and maintain data architectures for AI/ML model development and evaluation in national security programs.

You will build scalable pipelines, integrate sensor data, ensure data standardization, governance compliance, and collaborate with engineers, mission analysts, and data scientists to deliver high-quality datasets for advanced analytics.

Qualifications

• 10+ years of relevant experience.
• Understanding of GIS, data schemas, and geo-referencing.
• Knowledge of extraction and metadata specifications.
• Knowledge of RDBMS architectures and data normalization.
• Familiarity with enterprise geodatabases (SDEs).
• Proficiency with ArcGIS Suite, ArcGIS Online, Portal, Excel, Access, and SQL for spatial data management.
• Familiarity with ontology concepts in information systems.
• Strong collaboration skills across technical and mission-focused teams.

Responsibilities

• Design, develop, and maintain scalable data pipelines to ingest, process, and store data from sensors and platforms.
• Create and manage database schemas, tables, and infrastructure with automated data quality monitoring.
• Develop API-based workflows to securely move sensor data between government data platforms.
• Ensure sensor data complies with government schemas, formatting, and metadata requirements.
• Assess impact of new sensor data on databases, metadata models, APIs, and ETL processes.
• Develop preprocessing workflows for AI/ML model training and evaluation.
• Collaborate with cross-functional teams to optimize data workflows and pipeline reliability.

Skills

GIS

Data schemas

RDBMS

ArcGIS Suite

ArcGIS Online

SQL

Python

Team collaboration

Tools

ArcGIS Suite

ArcGIS Online

Portal

Excel

Access

SQL

Job description

We are seeking an experiencedExplotation Specialist/Data Stewardto join a high-performing team supporting advanced AI and machine learning initiatives for complex national security and intelligence missions.

This program focuses on evaluating AI models against Government datasets to assess their performance, resilience, and robustness across a broad spectrum of adversarial scenarios. The effort also includes testing and validating autonomous algorithms designed to support operational decision-making in dynamic mission environments.

As a Data Scientist, you will play a key role in designing, implementing, and maintaining the data architecture that supports AI/ML model development, testing, and evaluation. You will develop scalable data pipelines, integrate data from emerging sensors and platforms, and ensure data is standardized, accessible, and compliant with Government data governance requirements. Working closely with engineers, imagery scientists, and mission analysts, you will help deliver reliable, high-quality datasets that enable advanced analytics and operational decision-making.

Required Qualifications

• 10+ years of relevant experience. (A combination of years of experience, professional certifications, and education may be used in lieu of years of experience)
• Demonstrated understanding of GIS, data schemas, and the geo-referencing of information
• Knowledge of extraction and metadata specifications
• Knowledge of Relational Database Management System (RDBMS) architectures, best practices for data normalization, and performance tuning/optimization techniques
• Knowledge of enterprise geodatabases, such as Spatial Database Engines (SDEs)
• Knowledge of tools such as the ArcGIS Suite, ArcGIS Online, Portal, Excel, Access, and SQL for the storage, organization, and maintenance of spatial data
• Familiarity with ontology concepts as they relate to information systems, data modeling, and data relationships
• Strong collaboration skills with the ability to work effectively as a team player across technical and mission-focused teams
• Knowledge of scripting languages, such as R or Python

Preferred Qualifications

• Experience supporting NGA enterprise technologies and environments, includingNGA CORE,NGA MLOps, Government Authority to Operate (ATO) processes, and Government Non-Person Entity (NPE) certificates.
• Experience implementing processes and tools within organizations utilizing theScaled Agile Framework (SAFe).
• Experience developing dashboards and data visualizations to monitor operational pipeline health, data availability, currency, throughput, and overall system performance.

Key Responsibilities

• Design, develop, and maintain scalable data pipelines to ingest, process, and store data from emerging sensors and collection platforms.
• Create and manage database schemas, tables, and supporting infrastructure while implementing automated data quality monitoring and health alerts.
• Develop API‑based workflows to securely move sensor data between Government data platforms in accordance with program requirements.
• Ensure all sensor data complies with Government‑defined schemas, formatting standards, metadata requirements, and data governance policies.
• Assess the impact of new sensor data on existing databases, metadata models, APIs, schemas, and ETL processes to support seamless integration into operational data pipelines.
• Develop preprocessing and standardization workflows to prepare data for AI/ML model training, testing, and evaluation. Activities may include format conversion, imagery chipping, orthorectification, metadata normalization, and other transformation processes required to produce high‑quality analytical datasets.
• Collaborate with cross‑functional teams to optimize data workflows, improve pipeline reliability, and support the delivery of mission‑ready datasets for advanced analytics and machine learning applications.