Serve as a Data Scientist supporting the TSaaS program, delivering advanced analytics, machine learning models, and data-driven insights to support counterterrorism investigations and operational decision-making.
Collaborate with cross-functional teams to design, develop, and deploy scalable data solutions that align with mission objectives and evolving intelligence requirements.
Perform data analysis and visualization, tool and system development, and workflow automation to meet ad hoc and evolving requirements.
Design and implement ML, statistical analysis, and data analysis tasks; identify features and model variables; assess model outputs and perform remediation.
Conduct ETL work to aggregate and condition data from multiple repositories to provide novel insights.
Find and design new approaches for handling, analyzing, and using large volumes of data; address data handling, search, and retention issues.
Design, test, and validate software code to improve data search processes and data quality.
Automate routine workflows and data analysis steps; develop and maintain automated, reproducible workflows for data preparation, model development, and reporting.
Report results of analyses and provide actionable recommendations; maintain clear documentation and version control (e.g., Git) to ensure reproducibility and knowledge transfer.
Requirements
Possesses and applies comprehensive knowledge across key tasks and high impact assignments.
Evaluates performance results and recommends major changes affecting short-term project growth and success.
Collaborate with nontechnical, national security investigators and analysts to understand their data science needs, suggest solutions, and complete the work in a timely manner.
Design machine learning (ML), statistical analysis, and data analysis tasks.
Leverage existing and/or conduct custom Extract Transform Load (ETL) work to aggregate data from multiple repositories and condition the data to provide novel insights.
Interpret data, identify features and model variables, assess the quality of model outputs, generate alternatives, and conduct remediation.
Find and design new approaches to handling, analyzing, and using large volumes of data and/or data sets, and explore fundamental issues with data handling, search, and retention.
Design new software code to improve data search processes, and design, test, and validate the quality of data and data processes.
Automate routine workflows and data analysis steps to assist with workflow automation.
Report results of analyses and provide actionable recommendations.
Design and implement data science solutions that adhere to the principles of reproducible research, including maintaining clear documentation, using version control tools (e.g., Git), and ensuring that analyses are repeatable by others.
Develop and maintain automated, reproducible workflows for data preparation, model development, and results reporting, facilitating effective collaboration and knowledge transfer across the team.
Active Top Secret with eligibility for SCI or FS Poly.
3 years of relevant experience with a BS in Data Science, Mathematics, Information Science, Statistics, Engineering, Business Analytics, or related degree.
High proficiency in Python.
Organizational Skills: Can plan and prioritize work; good attention to detail.
Team Work: Comfortable working individually and as part of a team; able to challenge ideas constructively.
Leadership: Able to work effectively at all levels in an organization.
Communications: Ability to communicate clearly and efficiently, verbally and in writing; excellent active listening skills.
Quantitative Management: Ability to determine process measures and track effectiveness and efficiency.
Problem Solving: Ability to analyze problems, determine root cause, generate alternatives, and implement solutions.
Results oriented: Able to drive things forward regardless of personal interest in the task.