Data Scientist

C2 Essentials, Inc • Virginia Beach, VA

3d

About The Position

We are seeking highly skilled Data Scientists (DA II / DA III) to support enterprise data analytics, machine learning, and artificial intelligence initiatives within the Advana platform. The successful candidate will leverage advanced statistical modeling, machine learning, natural language processing, and deep learning techniques to develop predictive analytics solutions that drive mission outcomes, improve decision-making, and automate complex business processes.

Requirements

• Active Interim Secret Clearance or higher is required
• Python
• SQL
• Databricks (Lakehouse, Autoloader)
• Apache Spark (PySpark)
• Palantir Foundry (Ontology Development)
• Supervised Learning
• Unsupervised Learning
• Gradient-Boosted Trees
• Time-Series Forecasting (Prophet, SARIMAX, BSTS)
• Classification
• Regression
• Cluster Analysis
• Statistical Inference
• Regularization
• Dimensionality Reduction
• Deep Neural Networks (CNNs, Recurrent Networks)
• Object Detection
• Signature Verification
• Image Annotation
• Named Entity Recognition (NER)
• Topic Modeling (LDA, NMF)
• Text Extraction
• Sentiment Analysis
• Language Modeling
• Qlik Sense
• Palantir Foundry

Nice To Haves

• Experience supporting Federal Government, DoD, Financial Management (FM), or General Ledger (GL) data initiatives
• Experience working within the Advana ecosystem
• Experience developing and deploying machine learning solutions in cloud-based environments
• Familiarity with agile development methodologies and DevSecOps practices

Responsibilities

• Collaborated within cross-functional teams on the Advana platform to identify, design, and execute enterprise-level machine learning and predictive analytics solutions under an agile methodology
• Deployed supervised classification and regression models (including gradient-boosted decision trees) to automate high-priority risk-based sampling, improving risk detection while significantly reducing manual review workloads
• Engineered automated time-series forecasting pipelines in Databricks on Advana
• Built NLP text extraction and entity-tagging pipelines using LLMs to process and classify thousands of unstructured documents on the Advana platform, translating raw text into structured data
• Trained deep learning models to automate visual compliance checks and document verification, establishing continuous control testing and accelerating audit readiness workflows
• Managed production MLOps lifecycles and integrated model outputs into interactive visualization tools (Qlik Sense, Palantir Foundry) to deliver actionable business insights

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed