Data Scientist

Project Overview
The position will focus on building data ingestion and data transformation infrastructure to
interface with data repository application program interfaces (API) and build
AI/ML models to enterprise standards for data sharing with joint enterprise systems.

Responsibilities:
The Data Scientist will develop predictive models for operational logistics,
including:
o Demand Forecasting Models: Utilize time‐series analysis (e.g., ARIMA,
Exponential Smoothing) and machine learning models (e.g., Random
Forest, Gradient Boosting, XGBoost) for demand prediction and resource
optimization.
o Inventory Optimization Models: Develop algorithms to improve the
efficiency of supply chain operations, utilizing linear programming, mixedinteger
optimization, and supply chain simulation tools.
o Anomaly Detection: Implement unsupervised learning techniques such
as k‐means clustering, DBSCAN, and autoencoders for the detection of
anomalies in supply chain operations and logistics performance.
o Advanced Statistical Modeling: Apply advanced statistical techniques to
assess sustainment risks and optimize logistic workflows.
The Data Scientist will handle the breadth of tasks related to model
development, training, and continuous optimization of predictive models. The diversity
in machine learning algorithms, coupled with the need to manage and analyze large
volumes of data from multiple sources, requires a larger team. These professional will also
need to continuously monitor model performance, recalibrate models with updated data,
and deploy models in production environments.

Qualifications:
Bachelor's degree and a minimum of 7 years related experience,
US Citizen – TS/SCI clearance