Data Scientist

Ho-Chunk, Inc.•Fairfax, IA

3d•$140,000 - $153,000•Onsite

About The Position

All Native Group, a division of Ho-Chunk, Inc., is seeking a Data Scientist to support a Federal Agency enterprise data management and analytics program. Working with the Analytic team, the Data Scientist develops and refines machine learning and AI models, performs entity extraction and enrichment across large and complex datasets, and applies natural language processing techniques to unstructured data to advance the customer's mission objectives. This position supports an active federal contract. Any offer of employment is contingent on Government approval of the candidate and successful completion of the DEA security clearance process. The position is full-time, with flexible hours based on mission requirements. Work will take place at DEA facilities in Arlington, Virginia, and Merrifield, Virginia. Occasional CONUS travel may be required for meetings, conferences, or training. An active secret clearance is required.

Requirements

At least 3 years of in-depth experience with at least one analytical or statistical language, such as Python, R, or SQL.
At least 2 years of experience training custom machine learning and AI models, including supervised and unsupervised methods, and expertise in NLP focused on unstructured data.
At least 3 years of experience with SQL databases and coding.
At least 2 years of experience with data visualization tools.
At least 2 years of experience manipulating unstructured data.
Experience working in a fast-paced Agile development environment.
Bachelor's degree in data science or a related quantitative field; experience may be considered in lieu of education.
Active secret clearance is required.
Successful completion of a pre-employment drug screen is required; employees are also subject to random drug screens.

Nice To Haves

Experience supporting federal law enforcement or mission-focused data programs.

Responsibilities

Develop, train, and evaluate custom machine learning and AI models, including supervised and unsupervised approaches.
Apply natural language processing techniques to extract, enrich, and analyze unstructured data.
Improve and expand entity extraction processes by incorporating new entities and models.
Evaluate enterprise data holdings and develop models and techniques to enrich data for mission advantage.
Manipulate, cleanse, and prepare structured and unstructured data for model development and analysis.
Build data visualizations that communicate analytic findings to technical and non-technical stakeholders.
Collaborate within an Agile delivery team and participate in sprint planning, reviews, and continuous delivery.
Validate models for accuracy, stability, and bias.
Establish model monitoring and retraining to detect performance drift.
Package and deploy validated models, including required APIs and automation pipelines.
Design and implement ETL processes to prepare source data for model training.
Document model assumptions, data inputs, training parameters, and validation results.