Data Scientist, TRADOC G-2

Yorktown Systems Group, Inc. is an Equal Opportunity Employer. No employee or applicant for employment is denied equal opportunity because of race, color, sex, national origin, religion, age, disability, marital status, pregnancy, sexual orientation, gender identity, genetic information, any other non-merit-based factor, or other characteristics protected by law. As part of the company's equal employment opportunity policy, Yorktown Systems Group, Inc. will also take affirmative action as called for by applicable laws and Executive Orders to ensure that minority group individuals, females, disabled veterans, recently separated veterans, other protected veterans, Armed Forces service medal veterans, and qualified disabled persons are introduced into our workforce and considered for promotional opportunities.

Yorktown Systems Group, Inc. is a committed team of dedicated former military and civilian professionals who believe in providing ethical and quality services to Government customers. Our leadership team is composed primarily of Veterans who are now serving in a corporate environment rather than in uniform. Our customer's missions become our own and we are committed to working as a team to achieve success.

Because of the depth and experiences of our corporate leadership, we can assure all our customers that "we will do what we say we can do" and will focus on our customer's missions rather than corporate goals. Our business model is based on a personal commitment from our leaders to maintain contact with our customers to continually and consistently gauge our performance.

Yorktown Systems Group was founded on the idea that providing quality and ethical services with a laser focus on our customer's goals is an effective long-term business model. Our mission, therefore, is to help our customers meet their requirements and goals.

The contractor will not discharge or in any other manner discriminate against any employee or applicant for employment because such employee or applicant has inquired about, discussed, or disclosed the compensation of the employee or applicant or another employee or applicant. This provision shall not apply to instances in which an employee who has access to the compensation information of other employees or applicants as a part of such employee's essential job functions discloses the compensation of such other employees or applicants to individuals who do not otherwise have access to such information, unless such disclosure is in response to a formal complaint or charge, in furtherance of an investigation, proceeding, hearing, or action, including an investigation conducted by the employer, or is consistent with the contractor's legal duty to furnish information.

Summary:

Yorktown Systems Group is seeking a highly qualified Data Scientist to provide professional services and support to the Training and Doctrine Command (TRADOC) G-2. The TRADOC G-2 facilitates and acts as the principal enabler for continuous learning across all TRADOC lines of effort through acquiring, analyzing, creating, organizing, applying, and transferring data, information, and knowledge in the context of current and future operations. The G-2 is responsible for delivering the Operating Environment to facilitate the training of deploying units on joint, national, and interagency information, emerging asymmetric capabilities gleaned from world-wide operations; integrating processes, practices, concepts and materiel capabilities into Joint and Service DOTMLPF solutions; and coordinating with the training centers to provide realistic enemy and environmental signatures into models and simulations in support of realistic training.

The Data Scientist will assist in providing a realistic and relevant Operational Environment (OE) across all TRADOC lines of effort. Providing the OE to customers take many forms, but all rely on the quality and relevance of the data which is the foundation for providing and organizational asset to drive core mission requirements are critical to fundamentally changing the way in which the OE is seen and delivered.  The application of Data Science concepts, processes and technologies such as cloud and web enabled data and analytics, machine learning, artificial intelligence, and even process automation are key enablers to continue the progress of the past years in support of the G-2’s move to data-centricity. The Data Scientist will work with G-2 Information Management and Data Science teams to support the TRADOC Data Lake and Analytics Capability (TDLAC) on the TRADOC G-6 hosted cloud with an endstate of supporting the data-centric goals of the G-2, deployed and available to users, on the TRADOC Microsoft Azure Cloud.

Specific duties may include, but are not limited to:

• Key task areas are:
  • Execution and maturing of OE Self-Service Analytics and Data Ingest
  • Product improvements to GEODE, enhancing search and discovery as well as recommender capabilities for users by profile(s)
  • Training for data stewards, citizen data scientists and novice users of OE data
  • Maturing governance and policy, including prioritizing effort via the Data and Analytics Governance Council (DAGC), and subordinate working groups
  • Developing solutions for selected Data Science Use Cases, and delivery of Minimum Viable Product (MVP)
  • Maximize use of “as a service” Microsoft Azure Cloud Tools, and identifying and integrating appropriate Machine Learning (ML) and Artificial Intelligence (AI) techniques 
  • Updates and maintenance of the OE Ontology Version 3 and beyond   and the Changing Character of Warfare (CCOW) ontology and   internal and external data source curation. 
  • Planning, executing, and implementing of a data science training plan, an OE data implementation plan for sources internal and external to G-2, and data science use case process plan.
• Deploy and manage a DEVSECOPS approach for the development, testing/staging, and production environments for storage, analytics and/or applications development, on the TRADOC Commercial Cloud, MS Azure, and/or contractor cloud solution, as appropriate. Maximize use of PaaS and SaaS approaches for unclassified CUI and publicly available data.
• Provide Subject Matter Expertise (SMEs) to lead Data Science Work Groups that solve data science problems using recommended principles, approved architecture, task organization, governance, tasks/subtasks necessary to support the G-2 data centric organization mission.
• Execute a minimum of 4 Data Science, Remote Process Automation, Intelligent Automation, or Advanced analytic use cases culminating in the production delivery of associated analytics and user-facing applications. Integrate Athena PMESII-PT variable models for use across the TDLAC, including connected data preparation and output visualization.
• Develop a plan for data science training (onboarding, quarterly, bi-annual, and annual), mentoring, and facilitating as it pertains to data science tools and techniques which are key to the effective use of Data Science Teams.  Focus audiences include Data Stewards, Citizen Data Scientists, and all TRADOC G-2 personnel with training specifically designed to support the many skill levels (novice, intermediate, expert) members currently required for TRADOC G2 as a Data Centric Organization. 
• Provide an OE Data Implementation plan that includes the principles put forth in the Army Data Strategy and at a minimum describes a global, standards-based environment where data and information are visible, accessible, understandable, trusted, and interoperable throughout its lifecycle, for all authorized users when needed and regardless of location or access device This should align with the missions, goals and challenges identified in the Data-Centric strategic roadmap, August 2020.
• Continue implementation of the TRADOC G2 OE Ontology and CCOW as part of the Enhanced Search Capability. Provide essential elements of governance for the OE Ontology in support of Data Science, including Knowledge Management, Data Mining, and Data Management and Integration.
• Ingest prioritized internal OE data sources into the TRADOC Data Lake and Analytic Capability (TDLAC) with load determined by available resources and a plan for identifying additional source material such as historical information gathered by SMEs and sources utilized in the development of OE products.

Required Qualifications:

• Relevant Data Science experience. 5 years with BS or 3 years with MS in related field
• Project management experience. PMP preferred
• Ability to lead project design and estimation
• Ability to lead the Data Science contract team
• Ability to liaison with the government DS lead

Desired Qualifications:

• Experience with programming languages such as Python or R
• Experience creating visualizations and models with commercial software such as PowerBI or open source alternatives
• Experience programmatically creating dashboard views with visualization software
• Experience programmatically processing source data in various formats including SQL Databases, Raw CSVs, and streamed data sources
• Experience with a distributed computing framework such as Spark
•  Experience with a working with and processing data from data streaming source such as Apache Kafka
• Experience with Microsoft Azure Data Science capabilities
• BA/BS Degree in STEM rigorous field such as Statistics, Mathematics, Engineering, Physics, Computer Science 

Clearance:  Ability to obtain Secret clearance is required.

Location:  FT Eustis, VA

Travel: Travel is not required.