Staff Product Data Scientist

Role Overview

• Define, champion, and execute a strategic roadmap for measuring impact across PandaDoc, focusing on high-leverage business questions related to customer workflows, churn risk, and long-term value (LTV).
• Design, implement, and rigorously analyze complex A/B tests, multivariate experiments, and adaptive experimentation methods, including the application of Bayesian experimentation, to assess the effectiveness of proposed product changes and business levers.
• Apply advanced causal inference techniques (e.g., difference-in-differences, synthetic control, propensity score matching, and instrumental variables) to scenarios where randomized controlled trials (RCTs) are infeasible.
• Conduct complex, proactive, and exploratory analysis to discover latent user behavior, emerging trends, and root causes of changes in key metrics, translating these findings into actionable product and business insights.
• Define, instrument, and govern a unified Key Performance Indicator (KPI) framework that maps low-level product health metrics to high-level business outcomes, ensuring consistent and scalable measurement across the organization.
• Partner with Data Engineering to design and build scalable, self-serve experimentation tooling and reusable analytical assets and frameworks (e.g., causal machine learning models) that empower other analysts and data consumers.
• Act as a strategic thinker by translating complex statistical findings into clear, compelling, and actionable business narratives for cross-functional partners and senior leadership (VP/C-suite), driving strategic decisions and investment priorities.
• Serve as a technical subject matter expert, training and mentoring junior and mid-level data scientists on best practices in statistical rigor, experimental design, and causal modeling.

Requirements

• 6+ years of professional experience in an applied data science, economics, or product analytics role, with a proven track record of leveraging experimentation and causal inference methods to drive significant business impact.
• B.A. or B.S. in Mathematics, Statistics, Economics, Computer Science, or a related quantitative discipline. A Master’s degree in a quantitative field (e.g., Statistics, Data Science, Econometrics, Operations Research) is preferred, but not required.
• Demonstrated expertise in applying a wide range of Causal Inference methods, e.g. Quasi-Experimentation, Matching Methods (PSM), Difference-in-Differences, and/or Instrumental Variables.
• Expertise in advanced statistical methodologies for A/B testing, including sample size calculations, sequential testing, dealing with interference/network effects, variance reduction techniques (e.g., CUPED), etc.
• Mastery of advanced statistical modeling, time-series analysis, and quantitative methods necessary to perform thorough exploratory data analysis, produce timely insights, and provide actionable recommendations.
• Advanced proficiency in Python or R for statistical modeling, with experience using relevant data science packages (e.g., SciKit-Learn, numpy, pandas).
• Expert-level proficiency in SQL and experience working with established data warehouses (e.g., Snowflake, Postgres).
• Experience with data transformation and workflow management tools such as dbt, Airflow, or Databricks is a strong plus.

Tech Stack

• Airflow
• Numpy
• Pandas
• Postgres
• Python
• Scikit-Learn
• SQL

Benefits

• Our benefits include tremendous career growth opportunities, a competitive salary, health and commuter benefits, company paid life & disability, 20+ PTO days, 401K and FSA plans,
• of course, a fun team of Pandas to work with!