Data Scientist - Causal Inference and Experimental Design, Marketing Science R&D Facebook
Seattle, WA

Job Description

Marketing Science R&D is an interdisciplinary team of data scientists focused on research that improves measurement and ads delivery on our platform. The team's expertise spans domains, including causal inference, survey methodology, machine learning, cryptology, location and identity prediction algorithms. We develop methodologies, design and prototype solutions, and partner with our engineering and product colleagues to scale these solutions such that millions of advertisers can benefit.

We're looking for researchers and data scientists with expertise in causal inference to recognize new opportunities and help build highly-scalable, scientifically rigorous measurement and ads delivery systems. Challenges include using machine learning to scale variance reduction techniques to millions of advertisers' experiments, to identify heterogeneous treatment effects with computational efficiency, to enable causal inference with diverse and incomplete observational data, and to ensure generalizability from partial or unrepresentative data. Team members will pursue deep technical knowledge of our ads and measurement systems at Facebook, and research new approaches and algorithms to advance the state of causal inference within advertising.

RESPONSIBILITIES

* Research opportunities to develop and implement new methods or algorithms for causal inference to improve ads delivery and measurement for advertisers



Assess the validity and rigor of new data sources and approaches, establishing scalable validation frameworks for ongoing evaluation

Work both independently and build cross-functional relationships with Engineering, Product and Analytics to shape long-term product roadmaps with a balance of technical rigor and strategic considerations

Learn new tools, systems and languages quickly as required by the particular project you are working on

Apply excellent communication skills to engage diverse audiences on technical topics and nuanced insights

MINIMUM QUALIFICATIONS

* PhD in Economics, Political Science, Statistics, Psychology, or related field, or a Master's within one of these fields combined with 3+ years of hands-on research experience in the social or biomedical sciences, internet or advertising industry architecting and implementing experimentation or causal inference-focused solutions



Experience with at least two of the following: Experimental Design, Analysis of Experiments, Observational Causal Inference, and Quasi-Experimental Methods

Causal inference-related patents, conference presentations, academic papers or other indicators of research proficiency in industry-grade causal inference

Experience addressing challenges that emerge from missing or unrepresentative data

Knowledge with Python and/or R

PREFERRED QUALIFICATIONS

* Experience with online advertising, targeting, optimization and measurement systems



Development experience specific to experimentation platforms

Proficiency with machine learning, deep learning and advanced statistical modeling

Experience with Stan or JAGS

Experience with Presto, Hive or Spark SQL

Facebook is committed to providing reasonable accommodations for qualified individuals with disabilities and disabled veterans in our job application procedures. If you need assistance or an accommodation due to a disability, you may contact us at accommodations-ext@fb.com.