Senior Data Scientist

SOSi; United States; Remote; USD 100,000 - 130,000; Full time

Job summary

A leading defense and government services integrator is seeking a Senior Data Scientist to develop and sustain a scalable data ecosystem for enhancing interoperability and analytics for a DoD customer. This role involves designing advanced machine learning models, managing data provenance, and implementing Agile methodologies. The ideal candidate will hold a Master's in Data Science or equivalent experience, with proficiency in Python and machine learning frameworks. The position offers a unique opportunity to impact national security missions.

Qualifications

• Active TS/SCI Clearance.
• Demonstrated experience in building and validating AI/ML models.
• Knowledge to develop advanced machine learning models.

Responsibilities

• Design and implement advanced ML models and statistical methods.
• Conduct data provenance tracking for compliance.
• Implement sprint-based Agile methodologies.

Skills

Machine Learning model development

Python

TensorFlow

Scikit-learn

Data provenance tracking

Agile methodologies

Education

Master’s degree in Data Science

Tools

Databricks

Apache Spark

Job description

Founded in 1989, SOSi is among the largest private, founder-owned technology and services integrators in the defense and government services industry. We deliver tailored solutions, tested leadership, and trusted results to enable national security missions worldwide.

Job Description

SOSi is seeking a Senior Data Scientistto support mission requirements for a structured approach to further develop, integrate, and sustain a scalable, federated data ecosystem that enhances interoperability, governance, and mission-driven analytics for a DoD customer. The primary objective of the program is to bridge the operational gaps between DoD, IC, interagency, and non-traditional international partners to enable real-time information sharing, dynamic data integration, and mission-tailored analytical capabilities.

• The contractor shall design and implement advanced ML models and statistical methods to optimize forecasting, risk assessment, and decision-making processes.
• The contractor shall conduct data provenance tracking, ensuring documentation of sources, transformations, and lineage for compliance with governance policies.
• The contractor shall submit the Data Provenance & Lineage Report, summarizing transformation workflows, feature engineering processes, and audit compliance.
• The contractor shall implement sprint-based Agile methodologies, ensuring rapid development cycles, backlog grooming, and alignment with mission requirements.
• The contractor shall provide a Rough Order of Magnitude (ROM) Estimate Report before each analytics project, detailing expected Full-Time Equivalent (FTE) hours, compute costs, storage consumption, and infrastructure requirements.
• The contractor shall conduct quarterly reviews to track cost efficiency, assess system performance, and optimize analytic workflows through the Quarterly Cost & Resource Utilization Report.

Qualifications

• Active TS/SCIClearance.
• Master’s degree in Data Science, Machine Learning, Statistics, or a related field, or;
  • nine (9) years of equivalent experience in AI/ML model development and deployment.
• Personnel must have demonstrated experience in building and validating AI/ML models using Python, TensorFlow, PyTorch, or Scikit-learn, integrating models into production environments, and optimizing performance for real-time analytics.
• Experience with Databricks, Apache Spark, or similar distributed data processing frameworks is required.
• Experience working with geospatial datasets and integrating AI/ML solutions into mission-critical applications.
• Possess the knowledge and capability to develop advanced machine learning models and optimize analytic workflows for predictive and prescriptive intelligence.
• Proficient in deep learning, supervised and unsupervised learning techniques, data wrangling, and feature engineering.
• Experience with data provenance tracking, model explainability, and bias mitigation in AI/ML applications is required.
• Personnel must be able to translate operational challenges into analytic solutions, ensuring integration of structured, unstructured, and geospatial data.

Preferred Qualifications:

• Desirable but not required certifications include Google Professional Machine Learning Engineer, Microsoft Certified: Azure Data Scientist Associate, or TensorFlow Developer Certification.

Additional Information

Working at SOSi

All interested individuals will receive consideration and will not be discriminated against for any reason.