senior-data-scientist

A/B testing requires power analysis, sample size planning, and sequential testing to ensure statistical validity. This Skill automates experiment design, calculates required sample sizes, and validates results against significance thresholds, enabling production teams to make data-driven decisions with confidence.

Production models need rigorous evaluation across multiple metrics, cross-validation, and reproducibility. This Skill provides a model evaluation suite with automated validation, interpretability tools, and config-driven pipelines that work with CSV, JSON, and SQL data sources.

Feature engineering involves automated generation, selection, and transformation of input variables. This Skill includes a feature engineering pipeline that handles these steps systematically, reducing manual effort while maintaining reproducibility and traceability.

Time-series and causal inference require specialized statistical modeling. This Skill supports both through regression, time-series frameworks, and causal inference methods, alongside config-driven automation and reporting that validates assumptions and generates business insights.

Yes. This Skill supports multiple data formats—CSV, JSON, and SQL—enabling integration with existing data pipelines. Config-driven architecture allows you to specify formats without code changes, streamlining preprocessing and pipeline orchestration.

The Skill provides production-grade Python tooling (Experiment Designer, Feature Engineering Pipeline, Model Evaluation Suite) designed for teams building data science at scale. Experience with statistical concepts, Python workflows, and model evaluation is assumed for production deployments.