Data Scientist 3 - 27918

HII's Mission Technologies division•Suffolk, VA

About The Position

Mission Technologies, a division of Huntington Ingalls Industries, is seeking a Data Scientist to support the Joint Training Synthetic Environment (JTSE) and JLVC Modernization effort under the Joint Staff J7 (JS J 7) contract. This role focuses on developing advanced analytics, AI/ML models, and data architectures that enhance joint training, simulation, and decision support capabilities.

Requirements

5 years relevant experience with Bachelors in related field; 3 years relevant experience with Masters in related field; 0 years relevant experience with PhD or Juris Doctorate in related field; or High School Diploma or equivalent and 9 years relevant experience.
Ability to obtain and maintain a Secret Clearance within 45 days of hire.
Experience building and deploying machine learning or statistical models in production or operational environments.
Strong knowledge of data processing, distributed data systems, and data architecture principles.
Proficiency in Python or R and experience with common data science libraries and toolkits.
Experience with data wrangling, feature engineering, and exploratory data analysis.
Understanding of AI/ML concepts including supervised/unsupervised learning, model evaluation, and performance metrics.
Experience preparing and maintaining technical documentation for datasets, models, and analytical workflows.
Ability to work within cross functional teams and manage multiple priorities.
Strong analytical reasoning and problem solving skills.
Experience working in Linux based environments.

Nice To Haves

Experience developing or fine tuning large scale or foundation models (LLMs, multimodal models).
Familiarity with modern AI/ML frameworks.
Experience deploying machine learning models into production or enterprise systems.
Knowledge of real time data processing and streaming technologies such as Kafka.
Familiarity with Joint Training and Simulation environments such as JTSE, JLVC, LVC, or similar DoD systems.
Understanding of data governance, data standards, and enterprise data strategy frameworks.
Experience working with synthetic data or simulation generated datasets.
Familiarity with MLOps/DevSecOps pipelines and secure model deployment practices.
Experience supporting joint, multi domain, or coalition operations.
Relevant certifications (AWS, Kubernetes, Security+, CISSP, or similar).

Responsibilities

Lead end to end data science workflows, including problem definition, data acquisition, feature engineering, model development, evaluation, deployment, and lifecycle monitoring.
Translate operational and training objectives into data driven solutions by defining analytical approaches and data requirements for integrating advanced AI/ML models into JTSE and Joint Training Tools.
Design and maintain scalable data pipelines and architectures that support real time and near real time ingestion, processing, and analysis of operational and test & evaluation data.
Develop, train, and fine tune machine learning models — including large scale and foundation models to enhance simulation fidelity, decision support, and training outcomes.
Ensure data consistency and interoperability across multiple sources, systems, and stakeholders within a unified analytics environment.
Integrate AI/ML models into simulation and synthetic environments, including the Fully Informed Simulation Environment (FISE), to support advanced analytics and dynamic scenario generation.
Define, implement, and enforce data standards, schemas, and governance practices to ensure data quality and compliance.
Support exercise planning, execution, and after action analysis by enabling predictive analytics, anomaly detection, performance metrics, and other advanced analyses.
Collaborate with cross functional teams — including government stakeholders and mission partners — to align data science solutions with operational requirements and modernization goals.
Conduct model validation, testing, and performance assessments to ensure accuracy, robustness, and mission alignment.
Identify and mitigate risks related to data quality, model bias, scalability, and operational performance.
Support MLOps/DevSecOps practices to enable secure, repeatable, and continuous delivery of data science capabilities.
Document data pipelines, models, methodologies, and analytical findings for technical and non technical audiences