Twitter serves the public conversation by encouraging people all over the world to connect, learn, debate and solve problems together. We believe conversation can change the world, and that’s why Tweeps (that’s what we call Twitter employees) come to work every day.
Twitter’s top objective is to increase the pace of high-quality product development by improving our use of data to understand the needs of users while respecting user data and privacy. Because experimentation is integrated into our product development, your work to advance our use of causal reasoning is crucial for accomplishing this objective.
You will be a key member of the Experimentation Data Science team working closely with data scientists, engineers, and product managers to drive a culture of causal reasoning, to develop methods in causal inference for data scientists and engineers, and to implement features that improve the design, analysis, and interpretation of experiments.
Drive the research direction in developing methods and tools that increase the rigor and efficiency of our experimentation platform and analyses that are constructed using causal inference techniques.
Lead education initiatives by conducting literature reviews and by promoting the adoption of good statistical practices through efforts such as instructing at Twitter University and building new processes.
Write and collaborate on production code in Scala to implement new methods.
Consult with other teams across Twitter on complicated experimental designs and on analyses estimating causal effects.
Advanced degree in a discipline that uses mathematical analysis and 2+ years of experience (or 4+ years of total experience).
Significant experience and excitement with one or more of the following: advanced statistical techniques for A/B testing, methods for experimental design, observational causal inference, or quasi-experimental analysis. Examples include: quantile testing, sequential testing, variance reduction techniques, variance estimation for ratio metrics, multi-level / hierarchical modeling, statistical surrogate modeling, matching methods, regression adjustment, structural equation models, instrumental variables, regression discontinuity design, and graphical approaches to causal inference.
Track record for executing independent projects and leading complex, multi-functional projects with several dependencies.
Strong proficiency with Python / R and SQL.
Excitement to work with production engineering systems that are written in Scala and Scalding.
Experience with scaling experimentation systems and Spark is a plus.
Job opportunities should be equal. We don't discriminate. Period. In legal terms, that means: Twitter is an equal opportunity employer and doesn’t discriminate based on race, color, ethnicity, ancestry, national origin, religion, sex, gender, gender identity, gender expression, sexual orientation, age, disability, veteran status, genetic information, marital status or any other legally protected status.
San Francisco applicants: In response to the San Francisco Fair Chance Ordinance, we’d like to mention that we consider qualified applicants with arrest and conviction records.