#3 - Data Scientist Senior - Causal Inference

Muttdata

9d•Remote

About The Position

Muttdata is seeking a senior Data Scientist to support a key engagement with a leading beverage company in Mexico. The role focuses on determining the causal impact of growth and marketing activities by designing experiments, estimating impact, and translating findings into decisions that improve customer acquisition, retention, and revenue. It sits at the intersection of statistics, economics, and marketing and involves close collaboration with marketing, growth, and commercial stakeholders, as well as Data Engineers and Analytics Engineers. A strong analytical profile, methodological rigor, and the ability to communicate findings to non-technical audiences are essential. A background in Economics or a similar quantitative field is highly valued. The Data Scientist will design and analyze experiments, apply causal inference when randomization is not possible, measure marketing performance, and develop analyses, features, and models using Databricks. The role also includes building predictive and segmentation models to support targeting and personalization.

Requirements

At least 3 years of experience in Data Science, Applied Statistics, Econometrics, or similar analytical roles.
Hands-on experience with Databricks, including notebooks, Spark/PySpark, and Delta Lake; required.
Hands-on experience designing and analyzing A/B tests and online/offline experiments.
Strong knowledge of causal inference methods and their assumptions, limitations, and practical application, including Difference-in-Differences, Synthetic Control, Matching, Instrumental Variables, and uplift modeling.
Strong foundations in statistics and econometrics, including hypothesis testing, regression, Bayesian and frequentist approaches, and time series.
Proficiency in Python, including pandas, PySpark, statsmodels, and scikit-learn, and advanced SQL.
Experience applying data science to growth, marketing, or commercial problems, such as campaign measurement, pricing, promotions, and customer analytics.

Nice To Haves

Degree in Economics, Econometrics, Statistics, or a related quantitative field, ideally focused on applied microeconomics or causal inference.
Experience in CPG, retail, consumer goods, or beverage industries.
Experience with Marketing Mix Modeling tools such as Meridian, Robyn, or PyMC-Marketing, and media attribution.
Experience with causal libraries such as DoWhy, EconML, or CausalML, and Bayesian modeling tools such as PyMC or Stan.
Experience with MLflow and Databricks workflows/jobs.

Responsibilities

Design, run, and analyze A/B tests and multivariate experiments, including sample-size and power calculations, randomization, guardrail metrics, and interpretation of results.
Apply causal inference techniques—including Difference-in-Differences, Synthetic Control, Propensity Score Matching, Instrumental Variables, Regression Discontinuity, and uplift modeling—to estimate the impact of marketing campaigns, promotions, pricing, and loyalty initiatives when randomization is not possible.
Measure and optimize marketing performance, including incrementality, attribution, ROI/ROAS, customer lifetime value (CLV), and marketing mix modeling (MMM).
Translate business questions from growth and marketing teams into well-defined analytical problems and experimental designs.
Develop analyses, features, and models on Databricks using notebooks, Spark, and Delta Lake, collaborating with Data Engineers and Analytics Engineers on data pipelines and analytical datasets.
Build predictive and segmentation models, including churn, propensity, and customer segmentation, to support targeting and personalization strategies.