Data Scientist (Washington DC-Baltimore Area)

Data Scientist – Advana / Machine Learning / Predictive Analytics

Clearance Requirement: Interim Secret or higher

Employment Type: Full-Time

Environment: Department of War (DoW) / Advana

Position Overview

We are seeking an experienced Data Scientist to develop and implement enterprise machine learning, predictive analytics, forecasting, natural language processing, and deep learning solutions within the Advana environment.

The ideal candidate will have hands-on experience building and deploying data-science solutions using Databricks , Python, SQL, machine learning frameworks, and large enterprise datasets. The position requires the ability to work collaboratively across functional, financial, technical, and data teams to translate complex mission and business requirements into scalable analytical solutions.

The Data Scientist will support use cases spanning predictive modeling, risk assessment, time-series forecasting, NLP/LLM-based document processing, deep learning, computer vision, and automated control testing.

Key Responsibilities

• Collaborate with cross-functional teams within the Advana platform to identify, design, develop, and implement enterprise machine-learning and predictive-analytics solutions.
• Participate in Agile development activities, including requirements development, backlog refinement, sprint planning, testing, demonstrations, and iterative model improvement.
• Develop supervised machine-learning models for classification and regression use cases.
• Develop and optimize gradient-boosted decision tree models and other appropriate machine-learning algorithms.
• Develop predictive models to support risk identification, prioritization, and risk-based sampling.
• Automate analytical processes that reduce manual review requirements and improve the identification of high-risk transactions, records, or activities.
• Engineer automated time-series forecasting pipelines in Databricks on Advana .
• Develop forecasting models to identify trends, patterns, anomalies, and future performance indicators.
• Build Natural Language Processing (NLP) pipelines to extract, classify, and structure information from unstructured documents.
• Apply Large Language Models (LLMs) to text extraction, document classification, entity recognition, and entity tagging.
• Transform unstructured text into structured datasets suitable for downstream analytics and reporting.
• Develop and train deep-learning and computer-vision models to support visual compliance checks, document verification, and automated control testing.
• Perform feature engineering, model selection, model training, validation, testing, tuning, and performance evaluation.
• Develop reproducible and scalable data-science workflows within Databricks.
• Query and manipulate large datasets using SQL and Python/PySpark .
• Collaborate with data engineers to ensure appropriate data availability, quality, transformation, and pipeline integration.
• Collaborate with analysts and functional SMEs to validate model outputs and translate results into actionable insights.
• Document model assumptions, methodologies, data sources, performance metrics, limitations, and results.
• Communicate complex analytical and machine-learning findings to technical and non-technical stakeholders.

Required Qualifications

• Hands-on experience developing data-science or machine-learning solutions within Advana .
• Strong hands-on experience with Databricks .
• Advanced proficiency in Python for data science and machine learning.
• Strong proficiency in SQL .
• Experience developing supervised classification and regression models .
• Experience with machine-learning algorithms, including gradient-boosted decision trees .
• Experience developing time-series forecasting models or pipelines.
• Experience with NLP , text extraction, document classification, or entity tagging.
• Experience using or integrating LLMs into data-processing or analytical workflows.
• Experience with model training, validation, testing, tuning, and performance measurement.
• Ability to work with large structured and unstructured datasets.
• Strong analytical, statistical, and problem-solving capabilities.
• Experience working collaboratively within Agile and cross-functional teams.
• Strong written and verbal communication skills.
• Ability to explain complex data-science concepts and findings to both technical and non-technical stakeholders.
• Interim Secret clearance or higher.

Preferred Qualifications

• Experience with deep learning and computer vision .
• Experience developing automated visual compliance or document-verification solutions.
• Experience with PySpark and distributed data processing.
• Experience supporting Federal Financial Management, audit readiness, financial risk analysis, or compliance use cases.
• Experience developing production-oriented ML workflows or MLOps capabilities within Databricks.
• Familiarity with model monitoring, versioning, governance, and lifecycle management.
• Experience working with DoW enterprise data.
• Navy Financial Management experience is a plus.

Key Technologies & Skills

Advana | Databricks | Python | PySpark | SQL | Machine Learning | Predictive Analytics | Classification | Regression | Gradient Boosting | Time-Series Forecasting | NLP | LLMs | Entity Extraction | Deep Learning | Computer Vision | MLOps | Agile

Security Clearance

Candidates must possess an Interim Secret clearance or higher and maintain the required clearance throughout the period of performance.