Senior Data Scientist

Job DescriptionJob Description Position Title: Senior Data Scientist Location: Washington, D.C. 20024 Duration: 1-year base period with four (4) one-year option periods and one (1) six-month extension Required experience for each Data Scientist includes the following: Masters, Ph. D., or doctorate-level equivalent degree in data science, machine learning, computer science, mathematics, or a related field; OR 10 years of applied work experience in any of the same fields.Five (5) or more years of hands-on experience in each of the following: Designing, implementing, and maintaining advanced AI systems and predictive models, including both supervised and unsupervised models.Developing analytic rules and models using leading edge analytic tools and best practices.Developing regression, classification, and other statistical models to identify anomalies, patterns, and predictive variables.Three (3) or more years of hands-on experience in each of the following: Providing data support for criminal investigations into financial fraud or abuse of government funds.Manipulating data in Python. (Pandas required.)Working in the modern cloud environment (Azure/AWS/GCP). Certifications preferred.Two (2) or more years of hands-on experience in each of the following: Conducting advanced data analysis in SQL (SQL Server and PostgreSQL).Developing and scaling NLP solutions.Presenting methods and findings to technical and non-technical stakeholders, orally and in written products/visualizations. SPECIFIC TASKS Data Analytics Services Assist Technology Solutions Division (TSD) with data analytic products by providing highly skilled and authoritative expertise on analytic methods.Perform data quality analysis on source tables to identify any abnormalities or inconsistencies.Review, maintain, and provide support using all existing loan fraud indicators developed by TSD.Develop and refine repeatable processes for efficiently combining and analyzing large data sources (including relational tables, structured and unstructured datasets).Collaborate closely with criminal investigators to determine and execute strategies to support loan fraud cases; proactively address and communicate potential data quality issues and adapt analysis to shifting case needs; adhere closely to federal rules of criminal procedure governing protected information (e.g., Rule 6(e)).Design, develop, test, calibrate, and implement advanced statistical and machine learning models targeted at identifying financial fraud, improper payments, or noncompliance within SBA programs.Utilize indicators of potential loan fraud, improper payments, or non-compliance to develop and test predictive models.Assist in developing case leads for SBA OIG investigations based on model outcomes.Coordinate with the Data Engineering Team to ensure system architecture is designed to efficiently support machine learning models.Integrate and scale natural language processing methods to parse, clean, and analyze large corpora of unstructured or semi-structured text data, utilizing OCR, semantic similarity algorithms, and large language models as needed.Provide detailed documentation of all methodology, test models, and production models; maintain records in compliance with criminal evidentiary requirementsDevelop visualizations and dashboards to demonstrate methodological choices, outcomes, and predictive capabilities of machine learning models; iteratively solicit and integrate end user feedbackProvide outcomes and recommendations in multiple formats, including data summaries and visualizations for investigative staff, and executive summaries for SBA OIG leadership.Create programming and automation techniques to improve task efficiency using tools such as SharePoint, Python, Microsoft Excel, Power BI, Power Apps, and others.Identify new business questions to expand the scope of analysis and reporting.