Data Scientist

The Bison Group•Washington DC, DC

12d

About The Position

Bison Group – Mission First. People Always. At Bison Group LLC, we’re more than a defense contractor — we’re a people-focused small business with a strong culture built on trust, respect, and impact. We value every member of the team, foster open communication without the layers of a big corporation, and stand firmly behind our commitment to the veteran community through real, tangible action. When you join Bison Group, you’re not just filling a role — you’re stepping into a mission-critical environment where your work directly supports national security objectives. Here, your skills are recognized, your growth is encouraged, and your contributions have a clear purpose. 4~5 years of work experience as data scientist with strong knowledge of statistical modeling, machine learning experience using Python and R, hands-on experience with AWS cloud-native services (e.g., S3, RDS, OpenSearch, Lambda), and a working knowledge of Bank Secrecy Act (BSA) data. Practitioner should be able to: Design, develop, and deploy machine learning models and statistical algorithms to detect financial crime patterns (e.g., structuring, layering, smurfing) using BSA/AML transaction data Perform exploratory data analysis, feature engineering, and model validation using Python / Jupyter Notebook, PySpark, Pandas and R. Demonstrate experience with SQL for complex querying and analyze large-scale structured and unstructured datasets stored in AWS S3, PostgreSQL RDS, OpenSearch instance. Collaborate closely with compliance analysts and investigators to translate regulatory and investigative requirements into data analyses and analytical models Produce visualizations and written findings for both technical and non-technical stakeholders, as needed. Maintain documentation for data pipelines, model logic, and analytical findings in accordance with agency or organizational standards Participate in peer code reviews and contribute to best practices for reproducible data science workflows

Requirements

4-5 years of work experience as data scientist with strong knowledge of statistical modeling
Machine learning experience using Python and R
Hands-on experience with AWS cloud-native services (e.g., S3, RDS, OpenSearch, Lambda)
Working knowledge of Bank Secrecy Act (BSA) data
Experience using open source machine learning frameworks such as scikit-learn and tensor flow to answer business questions using proprietary data
Experience with statistical analysis and correlating disparate data
Experience with probabilistic modeling and/or predictive modeling
Experience with performing data analysis using scripting languages such as python, R, MATLAB, and Spark
Experience implementing machine learning processes into production software applications
Experience using big data tools to answer business questions using proprietary data
Experience in building property graphs from multiple data sources to perform network analytics
Analyze large, noisy datasets and identify meaningful patterns that provide actionable results
Minimum Bachelor’s degree in engineering, Data Science, Statistics, Mathematics, Computer Science, or a related quantitative field
Top Secret clearance

Responsibilities

Design, develop, and deploy machine learning models and statistical algorithms to detect financial crime patterns (e.g., structuring, layering, smurfing) using BSA/AML transaction data
Perform exploratory data analysis, feature engineering, and model validation using Python / Jupyter Notebook, PySpark, Pandas and R.
Demonstrate experience with SQL for complex querying and analyze large-scale structured and unstructured datasets stored in AWS S3, PostgreSQL RDS, OpenSearch instance.
Collaborate closely with compliance analysts and investigators to translate regulatory and investigative requirements into data analyses and analytical models
Produce visualizations and written findings for both technical and non-technical stakeholders, as needed.
Maintain documentation for data pipelines, model logic, and analytical findings in accordance with agency or organizational standards
Participate in peer code reviews and contribute to best practices for reproducible data science workflows