Infrastructure Experimentation Data Scientist

As a Senior Data Scientist focused on Infrastructure Experimentation, you will join a data org of Analytics Engineers, Data Engineers, and Data Scientists who partner with our infrastructure engineering teams to measure, model, and surface the infrastructure impact of product experiments. You will work closely with partners in data science, platform engineering, and experimentation platform teams to build and maintain models and experimentation capabilities that predict the cost and performance implications of A/B tests, enabling experiment owners to make more holistic decisions that balance member impact with infrastructure performance.

The ideal candidate will excel in experimentation design and evaluation, causal inference, and applied machine learning, with a passion for applying these skills within the infrastructure domain.

In this role, you will:

● Build and maintain machine learning models that predict the infrastructure cost impact of A/B experiments, translating experimentally observed signals (e.g., request volume changes) into business and system metrics (e.g. projected annualized costs)
● Drive adoption of infrastructure metrics within the experimentation community through analysis, consultation with experiment owners, documentation, and training
● Partner with platform teams (Observability, Experimentation Platform) to improve the quality and coverage of infrastructure usage data feeding our models

● Extend our measurement framework to new metrics (e.g., latency) and new experiment types (e.g., infrastructure canary tests)
● Champion an infrastructure lens within the broader experimentation community,
helping shift culture toward reasoning about the full ROI and infrastructure impact of experiments
● Connect with the larger analytics and experimentation communities at Netflix to bring visibility to our work and learn from others

You are:

● Experienced in experimentation methodology and causal inference, with a strong foundation in A/B testing, treatment effect estimation, and statistical significance
● Experienced in building and maintaining machine learning models in production,
including the full lifecycle of training, evaluation, monitoring, and continuous
improvement
● Fluent in Python and SQL, with experience engineering data pipelines and working with large-scale data systems
● A strong collaborator who thrives in horizontal roles with broad stakeholder surfaces, comfortable influencing decisions through data and analysis rather than direct authority
● An exceptional communicator who can flex between technical and non-technical
audiences, translating statistical concepts for software engineers and business leaders alike
● Comfortable with messy, incomplete data environments and able to balance short term execution with a drive to improve data quality over time
● A strong product thinker who views data science outputs as products, taking an
end-to-end ownership mindset from data quality through to user adoption
● Comfortable with ambiguity, and thrive with minimal oversight and process
● Curious about infrastructure systems; prior experience in the infrastructure domain is a strong plus but not required; the ability and motivation to learn is essential