Data Scientist

About The Role

The role focuses on turning complex, high-volume behavioral and operational data into models that drive core product decisions — forecasting, anomaly detection, segmentation, and causal inference problems where the answer changes what the business does next.

You will work within a small, senior data science team embedded directly with product and engineering, owning analyses and models end-to-end from exploratory work through production deployment and measurement.

Key Responsibilities

• Design, build, and validate statistical and ML models — forecasting, classification, uplift, and anomaly detection — that ship to production and influence product and pricing decisions
• Run rigorous A/B test design and causal inference analyses (diff-in-diff, synthetic control, instrumental variables) on experiments with ambiguous or noisy data
• Build reproducible data pipelines in Python and SQL, partnering with data engineering to keep feature tables reliable and performant at scale
• Develop and maintain dashboards and self-serve analytics in tools like Looker, Tableau, or Hex that stakeholders actually use to make decisions
• Translate ambiguous business questions into well-scoped analytical problems, and communicate findings clearly to technical and non-technical audiences
• Deploy models via APIs or batch jobs using Airflow, dbt, and cloud infrastructure (AWS or GCP), with monitoring for drift and performance degradation
• Contribute to team standards for experimentation methodology, model documentation, and code review

What We Are Looking For

• 3–6 years of experience in data science, applied statistics, or ML, with a track record of models or analyses that shipped to production
• Expert-level SQL and strong Python (pandas, scikit-learn, statsmodels; PySpark a plus)
• Deep grounding in statistics: hypothesis testing, causal inference, regularization, and knowing when a simple baseline beats a complex model
• Hands-on experience designing and analyzing A/B tests, including power analysis and sequential testing pitfalls
• Experience working with large, messy datasets and the judgment to know when data quality issues invalidate results
• Strong communication skills — able to present methodology, uncertainty, and tradeoffs to senior stakeholders without overselling
• MS or PhD in a quantitative field (Statistics, CS, Economics, Operations Research) or equivalent practical experience. Bonus: experience with causal ML libraries (EconML, DoWhy), dbt/Airflow pipelines, or prior work in marketplace, fintech, or SaaS domains.