OPEN Data Jobs is seeking a Data Scientist in Washington, District of Columbia, United States for a hybrid work arrangement. You will turn difficult questions and complex data into evidence by collaborating with stakeholders to define what should be measured, assess data availability, select appropriate statistical or machine learning methods, and clearly communicate what the results do and do not establish. The role covers the full analytics lifecycle from exploratory analysis through model development, validation, interpretation, and ongoing performance assessment. You will examine data quality and bias, test assumptions, quantify uncertainty, compare alternatives, document methods, and ensure analyses are reproducible. When a model will be used repeatedly, you will help define how its performance should be monitored over time.

What you’ll build includes forecasting, classification, risk assessment, anomaly detection, segmentation, causal analysis, simulation, and optimization models; exploratory analyses to reveal distributions, relationships, outliers, missingness, and data limits; experimental or quasi-experimental designs, sampling plans, and evaluation frameworks; reproducible analytics pipelines, notebooks, code, data documentation, model cards, and validation reports; and decision briefs that communicate results, uncertainties, assumptions, limitations, and appropriate uses to technical and nontechnical audiences.

Who you are: you are rigorous about methods and candid about uncertainty. You prefer to limit claims to what the data supports and are willing to repor

OPEN Data Jobs is seeking a Data Scientist in Washington, District of Columbia, United States for a hybrid work arrangement. You will turn difficult questions and complex data into evidence by collaborating with stakeholders to define what should be measured, assess data availability, select appropriate statistical or machine learning methods, and clearly communicate what the results do and do not establish. The role covers the full analytics lifecycle from exploratory analysis through model development, validation, interpretation, and ongoing performance assessment. You will examine data quality and bias, test assumptions, quantify uncertainty, compare alternatives, document methods, and ensure analyses are reproducible. When a model will be used repeatedly, you will help define how its performance should be monitored over time.

What you’ll build includes forecasting, classification, risk assessment, anomaly detection, segmentation, causal analysis, simulation, and optimization models; exploratory analyses to reveal distributions, relationships, outliers, missingness, and data limits; experimental or quasi-experimental designs, sampling plans, and evaluation frameworks; reproducible analytics pipelines, notebooks, code, data documentation, model cards, and validation reports; and decision briefs that communicate results, uncertainties, assumptions, limitations, and appropriate uses to technical and nontechnical audiences.

Who you are: you are rigorous about methods and candid about uncertainty. You prefer to limit claims to what the data supports and are willing to repor