Agile Defense is seeking a Data Scientist to support the design, development, and operational deployment of scalable, AI-enabled data solutions. You will be part of a multidisciplinary team integrating advanced analytics and machine learning within the Department of Defense’s CDAO ADA IR program, working in mission-critical environments.

What You'll Do

Plan, develop, and maintain reusable services for data ingestion, transformation, and feature engineering that support AI/ML workflows.
Implement core data science capabilities, such as entity resolution and prediction, within secure, containerized environments following CI/CD standards.
Collaborate with DevSecOps engineers to integrate services into production using tools like Databricks, Docker, and Terraform.
Ensure services meet performance, reliability, and security requirements consistent with DoD enterprise architecture.
Develop and deploy ML models for tasks such as decision support, automation, and anomaly detection.
Select and implement modeling techniques using Python, Spark, or cloud-native ML frameworks like SageMaker and MLflow.
Maintain reproducibility and interpretability of model outputs to meet mission transparency requirements.
Package model inference services with well-documented APIs for integration into applications and dashboards.
Conduct exploratory data analysis to identify trends and opportunities within structured and unstructured datasets.
Develop data visualizations and summaries that support stakeholder understanding and team decision-making.
Translate analytical findings into actionable recommendations using visual, narrative, and quantitative strategies.
Contribute to a shared library of analysis templates, reusable queries, and analytic workflows.
Engage with product managers and mission users to define data and model requirements aligned with operational goals.
Work closely with engineers to ensure data science components align with technical constraints.
Participate in agile sprint planning, retrospectives, and demos.
Maintain strong documentation practices that enable handoff and reproducibility.

What We're Looking For

Active DoD Secret clearance (or ability to obtain).
U.S. Citizenship required.

Nice to Have

4+ years of experience in applied data science, machine learning engineering, or data pipeline development.
Proficient in Python, SQL, and distributed data frameworks like Spark and Databricks.
Experience developing ML models from training to deployment using tools like scikit-learn, TensorFlow, XGBoost, and MLflow.
Familiarity with MLOps, API development, and secure cloud-based environments like AWS, Azure, or Palantir Foundry.
Strong understanding of data validation, model testing, and performance evaluation techniques.
Experience with data visualization and storytelling using tools such as Tableau, Plotly, or Matplotlib.
Excellent technical communication skills, with the ability to explain complex concepts to non-technical audiences.

Technical Stack

Languages & Frameworks: Python, SQL, Spark, Databricks, PySpark, scikit-learn, TensorFlow, XGBoost, MLflow
Cloud & Platforms: AWS, Azure, Palantir Foundry
Infrastructure & Tools: Docker, Terraform
Visualization: Tableau, Plotly, Matplotlib

Team & Environment

You will be part of a multidisciplinary team integrating advanced analytics, machine learning, and engineering practices into mission-critical environments at Combatant Commands and Joint Staff.