Data Scientist (Vantage) - Clearance Required

Logistics Management Institute•Belcamp, VA

12h•Hybrid

About The Position

LMI is seeking a Data Scientist to assist with Army data model, pipeline, and visualization development. This Data Scientist will create data models working from mock visualizations and raw data inputs; leverage python, PySpark, Foundry, and code repositories to develop an architecture plan; extract, transform, and load data into Vantage; and use Vantage workshops to develop visualizations. Active Secret clearance required. Location: Hybrid; at least 3 days on client site in Crystal City VA or Aberdeen MD LMI is a new breed of digital solutions provider dedicated to accelerating government impact with innovation and speed. Investing in technology and prototypes ahead of need, LMI brings commercial-grade platforms and mission-ready AI to federal agencies at commercial speed. Leveraging our mission-ready technology and solutions, proven expertise in federal deployment, and strategic relationships, we enhance outcomes for the government, efficiently and effectively. With a focus on agility and collaboration, LMI serves the defense, space, healthcare, and energy sectors—helping agencies navigate complexity and outpace change. Headquartered in Tysons, Virginia, LMI is committed to delivering impactful results that strengthen missions and drive lasting value.

Requirements

Bachelor's degree in data science, mathematics, statistics, economics, computer science, engineering, or other related business or quantitative discipline required.
Active DoD Secret clearance required. Must have at a minimum, an Interim Secret Clearance.
10 years of experience with Python, and strong experience with PySpark or similar big data libraries.
Knowledge of Army Vantage and data environment standardization.
Experience working with data analysis tools including object-oriented programming (Python, Java, SQL, TypeScript), computational analysis tools (R, MATLAB), and associated data science libraries (scikit-learn).
Experience developing and implementing statistical, machine learning, and heuristic techniques to create descriptive, predictive, and prescriptive analytics as well as to develop statistical tests to make data-driven recommendations and decisions
Experience creating meaningful data visualizations and interactive dashboards using platforms such as Tableau, Qlik, Power BI, RShiny, plotly, or d3.js to communicate findings and relate them back to how insights create business impact
Experience with data modeling, building "objects" (e.g., "Soldier," "Tank," "Unit") and defining how they relate to one another in the Foundry environment.
Strong background in DevOps and Software Engineering, including GitLab CI/CD, Infrastructure as Code, and implementing Quality Assurance practices like Test-Driven Development (TDD) and unit testing (Pytest).
Proven ability to design and scale Medallion Lakehouse Architectures, implement Data Mesh concepts, and utilize Dimensional Modeling (Star Schemas) on cloud platforms like Databricks or DoD Advana.
Innovative problem solving and root cause identification skills.
Superior communication skills, both oral and written.
Able to work effectively at all levels of an organization.
Must be a team player and able to work with and through others.
Ability to influence and align others and move toward a common vision or goal.
Federal government agency experience required
Applicants must meet eligibility requirements for a U.S. Government security clearance. Only US Citizens are eligible for a security clearance. For this position, LMI will only consider applicants with security clearances or applicants who are eligible for security clearances, due to the nature of the work.

Nice To Haves

Master's degree (preferred) in data science, mathematics, statistics, economics, computer science, engineering, or other related business or quantitative discipline.
Experience with authoritative data sources, including IPPS-A / MILPDS, GCSS-Army, GFEBS, DTMS / MEDPROS.
Experience with Army Vantage
Experience with efforts focused on understanding interdependencies of programs within an organization.

Responsibilities

Extract, transform, and load data using big data platforms like Palantir Foundry, loading data into data visualizations, transforming data using python and low code data pipeline building tools.
Build low-code no-code applications that allow end users to see real-time readiness dashboards.
Automate and clean the ingestion of data from legacy systems so it’s useful for decision-making.
Create models to forecast equipment failures, personnel shortages, or budget overruns.
Help with feature writing, task decomposition, acceptance criteria, user stories, and processes for extracting dependencies from descriptive models.
Quickly answer critical information requirements by pulling data across different domains, ability to gather customer requirements and deliver a comprehensive statistical analysis to answer their questions.
Support project management over data activities to ensure timely delivery in a reactive and agile environment.
Engage technical and functional program SMEs, and key data stakeholders to understand business processes, analytical requirements, key data elements, data protection guidelines, etc.
Define and develop techniques to integrate, consolidate, and structure data for analytical use.
Create data pipelines in python, going from raw data to data products needed for visualization or other analytics products.
Understand and analyze complex and organization-specific datasets.
Transform data and analysis into informative visualizations and interactive dashboards using open-source and commercially available visualization and dashboard tools.
Propose alternative designs and processes to manage various types of data using both standard and custom tables and fields.
Provide recommendations for improvements in data strategies to include changes to governance, stewardship, integration, and standardization.