Causal ML

PwC - Causal ML

Experience: Senior Engineer with 5+ years of experience No of Positions: 2

Basic Qualifications:

• Experience designing and analyzing controlled experiments end-to-end (A/B tests, weblabs)including power/sample-size analysis, randomization, treatment-effect estimation, and evaluating against launch criteria.
• Working knowledge of causal graphs (DAGs) to reason about confounders, colliders, and mediators and derive valid adjustment sets for effect identification from observational data.
• Hands-on experience with observational estimators such as Double/Debiased ML

(DML), Propensity Score Matching (PSM), and Inverse Propensity Weighting (IPW), with sound judgment on their applications and limitations.

• Proficiency in Python and SQL, with experience building causal pipelines from raw data to defensible effect estimates.
• Ability to translate causal findings into incrementality/lift estimates and clear

recommendations for non-technical stakeholders, including honest discussion of assumptions and uncertainty.

Preferred Qualifications:

• Experience with causal inference libraries like DoWhy, EconML, CausalPy, and familiarity with additional quasi-experimental methods (e.g., synthetic control, difference-in-differences).
• Experience using LLM agents to assist the causal analysis loop (hypothesis generation, adjustment-set proposal, estimator selection, interpretation), along with awareness of their limitations and human-in-the-loop safeguards.
• Experience working with the AWS data and analytics stack (Redshift, S3, Lambda, ECS) at scale.