Causal ML Engineer - A/B Testing & Impact

Relha LLC; Los Angeles, Northern (CA, KY); Hybrid; USD 209,000 - 313,000; Full time

Benefits offered by this job

RSUs

Health insurance

Parental leave

Mental health support

Job summary

Snap Inc. is seeking a Machine Learning Engineer to design and build causal inference models that quantify impact and optimize decisions for users and advertisers.

The role involves productionizing uplift modeling and heterogeneous treatment effect estimation using both observational and experimental data. You will analyze A/B tests, collaborate with product and engineering to shape experimentation strategies, and evaluate tradeoffs between model complexity, bias, variance, and scalability in a

Qualifications

• Bachelor’s degree in CS, statistics, economics, or equivalent.
• 5+ years of post-Bachelor’s experience in ML with causal inference or experimentation.
• 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.

Responsibilities

• Design and build models that quantify causal impact and drive value for users, advertisers, and the business.
• Productionize causal machine learning solutions using observational and experimental data.
• Design, analyze, and interpret A/B tests and quasi-experiments with product/engineering partners.
• Evaluate tradeoffs between model complexity, bias/variance, scalability, and interpretability.
• Conduct code reviews and maintain scalable, maintainable infrastructure.

Skills

Causal inference

A/B testing

Experimentation infra

Python

Pandas

NumPy

scikit-learn

CausalML

EconML

DoWhy

Education

Bachelor’s degree

Master’s degree

PhD

Tools

CausalML

EconML

DoWhy

Job description

Snap Inc. is seeking a Machine Learning Engineer to design and build causal inference models that quantify impact and optimize decisions for users and advertisers.

The role involves productionizing uplift modeling and heterogeneous treatment effect estimation using both observational and experimental data. You will analyze A/B tests, collaborate with product and engineering to shape experimentation strategies, and evaluate tradeoffs between model complexity, bias, variance, and scalability in a