Data Scientist

VT Group•Mclean, VA

38d

About The Position

iota IT, a subsidiary of VTG, is seeking a Data Scientist in the National Capital Region. What will you do? Transform complex data landscapes and drive strategic insights as a Data Scientist at the forefront of innovative technological solutions! Identify and gather data from internal systems and external sources. Extract data using SQL, APIs, or data pipeline tools. Clean, transform, and validate data to ensure accuracy and usability. Engineer new features that enhance model performance. Analyze datasets to identify patterns, trends, and relationships. Use statistical techniques and visualizations to uncover insights and inform modeling choices. Build, test, and refine statistical and machine learning models. Evaluate models using appropriate metrics and validation strategies. Document methodology, assumptions, and results for reproducibility. Insight Generation & Communication Translate analytical findings into clear, actionable recommendations. Create visualizations, dashboards, and presentations for stakeholders. Communicate complex concepts in a concise and accessible manner. Deployment & Operationalization Collaborate with engineering teams to deploy models into production environments. Develop scalable model pipelines and monitoring frameworks. Support ongoing model maintenance and retraining. Experimentation & Causal Analysis Design, implement, and analyze A/B tests and other experiments. Apply causal inference techniques to measure the impact of initiatives. Collaboration & Continuous Improvement Partner with cross-functional stakeholders to understand business objectives and define data-driven opportunities. Translate ambiguous questions into structured analytical problems. Work closely with product, engineering, and business teams. Stay current with industry trends, tools, and best practices. Ensure ethical data usage and adherence to privacy and compliance standard

Requirements

Active Top Secret/Sensitive Compartmented Information (TS/SCI) clearance, with polygraph.
Bachelor's Degree in Computer Science, Engineering or related field.
Demonstrated experience with data engineering, to include designing and building data infrastructure, developing data pipelines, transforming/preparing data, ensuring data quality and security, and monitoring/optimizing systems.
Demonstrated experience with data management and integration, including designing and operating robust data layers for application development across local and cloud or web data sources.
Demonstrated work experience programming with Python
Demonstrated experience building scalable ETL and ELT workflows for reporting and analytics.
Demonstrated experience with general Linux computing and advanced bash scripting
Demonstrated experience with SQL.
Demonstrated experience constructing complex multi-data source queries with database technologies such as PostgreSQL, MySQL, Neo4J or RDS
Demonstrated experience processing data sources containing structured or unstructured data
Demonstrated experience developing data pipelines with NiFi to bring data into a central environment
Demonstrated experience delivering results to stakeholders through written documentation and oral briefings
Demonstrated experience using code repositories such as Git
Demonstrated experience using Elastic and Kibana technologies
Demonstrated experience working with multiple stakeholders
Demonstrated experience documenting such artifacts as code, Python packages and methodologies
Demonstrated experience using Jupyter Notebooks
Demonstrated experience with machine learning techniques including natural language processing
Demonstrated experience explaining complex technical issues to more junior data scientists, in graphical, verbal, or written formats
Demonstrated experience developing tested, reusable and reproducible work
Work or educational background in one or more of the following areas: mathematics, statistics, hard sciences (e.g. Physics, Computational Biology, Astronomy, Neuroscience, etc.) computer science, data science, or business analytics

Nice To Haves

Demonstrated experience with cloud services, such as AWS, as well as cloud data technologies and architecture.
Demonstrated experience using big data processing tools such as Apache Spark or Trino
Demonstrated experience with machine learning algorithms
Demonstrated experience with using container frameworks such as Docker or Kubernetes
Demonstrated experience with using data visualizations tools such as Tableau, Kibana or Apache Superset
Demonstrated experience creating learning objectives and creating teaching curriculum in technical or scientific fields

Responsibilities

Identify and gather data from internal systems and external sources.
Extract data using SQL, APIs, or data pipeline tools.
Clean, transform, and validate data to ensure accuracy and usability.
Engineer new features that enhance model performance.
Analyze datasets to identify patterns, trends, and relationships.
Use statistical techniques and visualizations to uncover insights and inform modeling choices.
Build, test, and refine statistical and machine learning models.
Evaluate models using appropriate metrics and validation strategies.
Document methodology, assumptions, and results for reproducibility.
Translate analytical findings into clear, actionable recommendations.
Create visualizations, dashboards, and presentations for stakeholders.
Communicate complex concepts in a concise and accessible manner.
Collaborate with engineering teams to deploy models into production environments.
Develop scalable model pipelines and monitoring frameworks.
Support ongoing model maintenance and retraining.
Design, implement, and analyze A/B tests and other experiments.
Apply causal inference techniques to measure the impact of initiatives.
Partner with cross-functional stakeholders to understand business objectives and define data-driven opportunities.
Translate ambiguous questions into structured analytical problems.
Work closely with product, engineering, and business teams.
Stay current with industry trends, tools, and best practices.
Ensure ethical data usage and adherence to privacy and compliance standard