Data Scientist

• Define measurement needs and assess whether available data supports stakeholder questions
• Select statistical and machine learning methods appropriate to the question and evidence
• Conduct exploratory data analysis covering distributions, relationships, outliers, missingness, and data limitations
• Develop forecasting, classification, risk, anomaly-detection, segmentation, causal, simulation, or optimization models
• Design experiments or quasi-experiments, sampling plans, measurement strategies, and evaluation frameworks
• Validate assumptions, compare alternatives and models, investigate errors, and quantify uncertainty
• Examine data quality and bias and interpret results in context
• Build reproducible analytical pipelines, notebooks, code, data documentation, model cards, and validation reports
• Communicate findings, uncertainty, assumptions, limitations, and appropriate uses to technical and nontechnical audiences
• Collaborate with subject-matter experts, analysts, engineers, stakeholders, and decision-makers
• Help define ongoing model performance assessment when models are used repeatedly

• Working foundation in statistics, probability, research design, machine learning, optimization, or another relevant quantitative discipline
• Ability to prepare, explore, and analyze data using Python, R, or SQL
• Attention to data quality and provenance
• Experience selecting methods, validating assumptions, comparing models, investigating errors, and interpreting results in context
• Reproducible practices using documented code, version control, peer review, traceable data transformations, and clear analytical records
• Ability to communicate uncertainty, bias, limitations, and appropriate use clearly
• Specific openings may require statistical inference, experimental design, forecasting, natural language processing, computer vision, econometrics, operations research, causal analysis, geospatial analysis, model risk, program evaluation, or applied AI
• Specific openings may require programming languages, statistical packages, ML libraries, cloud analytical environments, distributed-computing tools, domain datasets, visualization platforms, or documentation and review standards

Demonstrates expertise in statistical analysis, machine learning, and data exploration, with a strong focus on data quality and reproducibility. Proficient in communicating complex findings to diverse audiences and collaborating with stakeholders to drive data-informed decisions.

• Statistical Analysis
• Machine Learning
• Data Exploration
• Python Programming
• Reproducible Practices

• Statistics
• Probability
• Research Design
• Optimization
• Data Analysis
• Experimental Design
• Forecasting
• Natural Language Processing
• Causal Analysis
• Geospatial Analysis

• Communication
• Collaboration
• Attention to Detail

• Data Quality
• Model Validation
• Analytical Pipelines
• Model Performance Assessment
• Bias Interpretation

• Python
• R
• SQL
• Statistical Packages
• ML Libraries
• Cloud Analytical Environments
• Visualization Platforms