Machine Learning Engineer (Causal Inference)

Join Snap Inc., a leading social media platform, as a Machine Learning Engineer specializing in causal inference. In this role, you will design and build models that quantify causal impact, optimize decision-making, and drive value for users, advertisers, and the business. You will develop and productionize causal machine learning solutions, analyze and interpret A/B tests, and evaluate technical tradeoffs. You will also conduct code reviews, maintain high engineering standards, and contribute to rapid iteration cycles while ensuring methodological rigor.

• Concevoir et construire des modèles qui quantifient l'impact causal, optimisent la prise de décision et génèrent de la valeur pour les utilisateurs, les annonceurs et l'entreprise.
• Développer et mettre en production des solutions d'apprentissage automatique causal (par exemple, modélisation de l'élévation, estimation des effets de traitement hétérogènes) en utilisant des données d'observation et expérimentales.
• Concevoir, analyser et interpréter des tests A/B et des quasi-expériences ; collaborer étroitement avec les partenaires produits et ingénierie pour façonner les stratégies d'expérimentation.
• Skilled at solving open-ended problems with a mix of statistical thinking and engineering pragmatism
• Proficient in Python and common data/machine learning libraries (e.g., pandas, NumPy, scikit-learn, CausalM etc.)
• Strong understanding of causal inference and modern approaches to estimating treatment effects (e.g., meta learners, propensity score matching, instrumental variables)
• Experience with applied data science, including A/B testing, uplift modeling, and experimentation infrastructure
• Comfortable working independently and collaborating across cross-functional teams
• Strong communication and mentorship skills; able to translate technical insights for non-technical partners
• Experience designing and analyzing online experiments (A/B tests) and leveraging causal ML in production systems
• Demonstrated experience building models to support product decision-making and policy evaluation through causal techniques
• 5+ years of post-Bachelor’s experience in machine learning, with hands-on experience in causal inference or experimentation; or Master’s degree in a technical field + 4+ year of post-grad machine learning experience; or PhD in a relevant technical field + 2 years of post-grad machine learning experience
• Bachelor’s degree in computer science, statistics, economics, or a related technical field, or equivalent practical experience
• Advanced degree (MS/PhD) in a quantitative field such as statistics, data science, computer science, economics, or operations research
• Experience with causal inference libraries such as CausalML, EconML or DoWhy
• Background in deploying models in production settings and working with ML or experimentation infrastructure
• Deep understanding of experimentation nuances, including intent-to-treat (ITT) vs. ghost ad methodologies, and the trade-offs between frequentist and Bayesian inference for decision-making under uncertainty
• Experience applying causal inference in domains like personalization, ad or marketplace dynamics