Data Scientist

Environmental Protection Agency; Washington (District of Columbia); On-site; USD 90,000 - 130,000; Full time

Job summary

Environmental Protection Agency's Office of Inspector General is seeking a Data Scientist to develop data analytics and ML models in AWS and M365 environments, and to create visualizations for findings.

The role includes coding in SQL, Python, and R, documenting methodologies, and ensuring reproducibility of analyses for audits and investigations. Collaboration with teams and adherence to data governance are key.

Qualifications

• Experience building data pipelines and data cleaning
• Experience with ML models and testing in AWS/M365 environments
• Proficiency in SQL, Python, and R for data processing
• Experience creating visualizations with BI tools (Power BI)

Responsibilities

• Develop data analyses and statistical trends from datasets
• Create visualizations using BI tools and GIS platforms
• Review/optimize SQL, Python, and R code for ML models
• Maintain data dictionaries and document methodologies
• Support validation, testing, and reproducibility of analyses
• Participate in code reviews and QA for audits

Skills

Data analysis

Machine learning

SQL

Python

R

Power BI

ArcGIS Knowledge

ArcGIS Enterprise

SageMaker

AWS

M365

Job description

Open: September 1, 2026 — Closes: September 8, 2026

Summary

This position is located in the Office of Inspector General - Office of Data Analytics and Technology - Data Analytics Directorate. The OIG is an independent office within EPA that helps the agency protect the environment in a more efficient and cost-effective manner. We consist of auditors, program analysts, investigators, and others with extensive expertise. Although we are a part of EPA, Congress provides us with our funding separate from the agency, to ensure our independence.

Major Duties

As a Data Scientist GS-1560-09 your typical work assignments may include the following under supervision: At the direction of the Director or Team Lead and using established methods, create and model data analysis and statistical trends using data pipelines which includes data cleaning, feature engineering, design and implementation of machine learning models, including generative AI and agentic AI solutions, to support oversight projects and investigations in the Amazon Web Services (AWS) and Microsoft 365 (M365) environments. At the direction of the Director or Team Lead and using established methods, create visualizations for data analysis and findings using business intelligence tools, Link Analysis tools, and Machine Learning (ML) services such as Microsoft PowerBI, ArcGIS Knowledge, ArcGIS Enterprise, and Amazon SageMaker. At the direction of the Director or Team Lead, review and optimize SQL, Python, and R code related to (ML) models, queries, and database operations for efficient data access, processing, and reporting. Assists with technical documentation by creating data dictionaries, methodologies, and utilizing version control for traceability of the entire lifecycle of data and analytical models. Support data validation, testing, and monitoring of data analyses that support audits, evaluations, and investigations and participate in code reviews, quality assurance, lessons learned, and ensure reproducibility of the analyses. As a Data Scientist GS-1560-11 your typical work assignments may include the following under supervision: At the direction of the Director or Team Lead, create and model data analysis and statistical trends using data pipelines which includes data cleaning, feature engineering, design and implementation of machine learning models, including generative AI and agentic AI solutions, to support oversight projects and investigations in the Amazon Web Services (AWS) and Microsoft 365 (M365) environments. At the direction of the Director or Team Lead, create visualizations for data analysis and findings using business intelligence tools, Link Analysis tools, and Machine Learning (ML) services such as Microsoft PowerBI, ArcGIS Knowledge, ArcGIS Enterprise, and Amazon SageMaker. At the direction of the Director or Team Lead, develop or optimize SQL, Python, and R code related to (ML) models, queries, and database operations for efficient data access, processing, and reporting. Prepare and maintain technical documentation including data dictionaries and methodologies, and utilizes version control for traceability of the entire lifecycle of data and models. Support data validation, testing, and monitoring of data analyses that support audits, evaluations, and investigations and participate in code reviews, quality assurance, lessons learned, and ensure reproducibility of the analyses.