Data Scientist - Senior

GRVTY•Falls Church, VA

6d•$160,000 - $190,000

About The Position

GRVTY is seeking a motivated and experienced Data Scientist to perform data analysis via statistical and quantitative methods, develop visualizations to support decision making, and build software to enable thorough monitoring and management of data pipeline tasks. The ideal candidate brings deep expertise in data systems and a passion for solving complex analytical problems in support of Machine Learning model development and operational intelligence missions. This role will help accelerate the implementation of the NGA Maven Data Strategy and drive cross-departmental collaboration to enhance workflows and deliver greater productivity across labeling and imagery curation efforts.

Requirements

Active TS/SCI Clearance with the ability to obtain a CI/Poly
Experience working with AI/ML technologies and data systems
Experience working with multiple file types including: Geospatial file formats, JSON, XML, and related formats
3+ years of experience in quantitative analysis and data operations, including: Developing visualizations and processing complex data to create data-driven insights, Data manipulation and ETL procedures
Working knowledge of SQL and NoSQL database technologies
Development experience in Python and other languages for data cleaning and manipulation

Nice To Haves

Experience applying Natural Language Processing (NLP) algorithms to extract data from documents
Experience with enterprise NGA analytic modernization efforts such as SOM, Computer Vision, automated collection, or automated reporting, along with data standardization best practices
Demonstrated expertise in math, statistics, and quantitative analysis, including analytic techniques such as classification, regression, clustering, data reduction, and causal modeling

Responsibilities

Integrate emerging sensors and platforms into existing data pipelines and workflows, including: Developing pipelines and relevant data structures for emerging capabilities, Incorporating new data types into existing data workflows
Assess potential differences in metadata, data format, and data structure characteristics regarding changes to: Databases and schemas, APIs and other ETL-related processes, Ingestion and movement of data within the existing data operations pipelines
Conduct analysis of how emerging data impacts overall program data holdings from the perspective of: Machine Learning model development, Test and evaluation use cases, Real-world operational use cases
Evaluate and recommend solutions for partitioning new data types into training, test, and validation splits for effective ML model development and performance evaluation
Lead the design and application of methods to identify, collect, process, and analyze large volumes of data to build and enhance products, processes, and systems
Lead projects using advanced mathematical, statistical, and scientific techniques to: Examine complex mission and operational problems, Create insights from data
Build web scraping algorithms for imagery curation in accordance with customer data priorities
Integrate multiple data and intelligence sources in various formats for imagery curation to address gaps and meet project priorities
Support data analytics, data cleansing, analyst workflow efficiencies, and ETL transformation capabilities
Utilize statistical and analytic methods to support answering intelligence requirements and mission objectives
Build and integrate analytic tools and algorithms for imagery curation, acquisition, and chipping
Design methods and mechanisms to track, report, and monitor mission-specific objectives to maintain custody of training data priorities
Build software tools to manage labeling campaigns, including: Tracking unlabeled and labeled data and campaign status, Transferring label task information via API-based movement between platforms
Build software tools to: Filter and visualize data geospatially, Allow feedback entry and data analysis, Integrate with existing data management platforms
Conduct analysis of overall data holdings to support development of performant AI/ML models satisfying operational user requirements
Evaluate, monitor, and provide recommendations on training, test, and validation data splits for effective model development and performance evaluation