Machine Learning Scientist

Key Responsibilities

Develop and implement causal inference methodologies (e.g., A/B testing, propensity score matching, instrumental variables, difference-in-differences) to estimate the impact of marketing campaigns, promotions, and other interventions on eCommerce KPIs.
Conduct incrementality analysis to understand the true effect of marketing efforts on sales, customer acquisition, and retention, distinguishing between correlated and causal effects.
Collaborate with cross-functional teams, including marketing, product, and engineering, to define business problems, formulate hypotheses, and design experiments to test for causal relationships.
Build and optimize machine learning models to support causal analysis, including uplift modeling, heterogeneous treatment effect estimation, and causal forests.
Analyze large-scale datasets from multiple sources (e.g., transaction data, user behavior data, marketing spend) to identify patterns and generate actionable insights.
Perform advanced statistical analysis, including Bayesian methods and counterfactual modeling, to guide business decisions in areas like personalized recommendations, customer lifetime value (CLV), and marketing effectiveness.
Design and implement A/B tests and other experimental designs for measuring the impact of new features, strategies, or treatments in eCommerce environments.
Work with stakeholders to deliver clear, actionable insights on the incremental impact of different marketing and product strategies.
Stay up to date with the latest research and trends in causal machine learning, econometrics, and eCommerce analytics, and apply cutting-edge methods to improve business outcomes.
Document and communicate complex concepts and results clearly and effectively to both technical and non-technical stakeholders.

Required Qualifications

Master’s or Ph.D. in Statistics, Econometrics, Machine Learning, Data Science, Economics, or a related quantitative field with a focus on causal inference or impact analysis.
7+ years of hands-on experience in causal inference and machine learning within an eCommerce or retail environment.
Strong knowledge of causal inference techniques such as propensity score matching, instrumental variables, synthetic control methods, regression discontinuity, difference-in-differences, and uplift modeling.
Proficiency in Python or R, with experience in relevant libraries such as DoWhy, CausalML, EconML, or causalImpact.
Solid understanding of experimental design, A/B testing, and incrementality measurement in digital marketing, pricing, or promotion strategies.
Experience in working with large datasets from platforms such as Google Analytics, SQL databases, or big data tools like Spark and Hadoop.
Ability to build and optimize machine learning models for business impact, particularly in areas such as personalization, recommendations, and customer segmentation.
Excellent analytical and problem-solving skills, with a deep understanding of statistical analysis and machine learning.
Strong communication skills with the ability to explain complex causal models and incrementality findings to both technical and non-technical teams.

Preferred Qualifications

Experience in Bayesian causal inference and counterfactual analysis.
Familiarity with uplift modeling and heterogeneous treatment effect estimation to identify which users or segments respond best to interventions.
Experience with cloud platforms like AWS, Google Cloud, or Azure for deploying models in production environments.
Experience working with digital marketing data, eCommerce transaction data, and customer journey analytics.
Contributions to research papers, case studies, or conference presentations in causal machine learning or econometrics.