Sr. Data Scientist

Peloton•New York, NY

6h•$173,500 - $213,100•Hybrid

About The Position

Peloton is seeking a Senior Data Scientist specializing in Marketing Mix Modeling (MMM) to build and scale its in-house global marketing measurement capability. The role owns the development, validation, and evolution of statistical models that measure the incremental impact of marketing investment across channels, funnel stages, products, markets, and business outcomes. The position combines hands-on MMM development and statistical programming with the ability to explain complex analysis and turn it into actionable recommendations for Marketing, Media, Finance, and executive leaders. The Senior Data Scientist will work across custom-built Bayesian models and established MMM frameworks, understanding and adapting underlying code and methodologies as analytical and business needs evolve. The role also develops response and saturation curves, budget optimization and scenario-planning capabilities, and models of marketing’s effects on intermediate outcomes such as brand health and organic traffic. The goal is a statistically credible, technically scalable, and actionable global measurement capability that informs marketing and financial decisions. The role partners with Media, Marketing, Finance, Data Engineering, and Analytics teams to explain performance drivers, recommend investment and channel strategies, and build reliable recurring model workflows and decision-support tools. It also establishes documentation, quality-assurance standards, model governance, and repeatable processes.

Requirements

5–6+ years of professional experience in Data Science, Marketing Science, Marketing Analytics, Econometrics, or a related quantitative field.
Demonstrated hands-on experience developing and evolving Marketing Mix Models; direct MMM modeling experience is required.
Strong understanding of MMM methodology, including adstock and carryover transformations, response and saturation curves, diminishing returns, baseline and control variables, model specification, and model validation.
Strong statistical programming skills, particularly in Python and/or R, including the ability to understand, debug, modify, and extend modeling code.
Experience working across different MMM approaches and adapting methodologies to the analytical and business problem.
Experience developing response and saturation curves and marketing budget optimization or scenario-planning methodologies using MMM outputs.
Strong understanding of marketing measurement concepts, including incrementality, CAC, ROI, marginal effectiveness, response rates, attribution, and funnel dynamics.
Ability to interpret how media strategy, buying approach, audience strategy, and optimization objectives influence marketing performance.
Demonstrated ability to translate sophisticated analytical work into clear business narratives, recommendations, and executive-level presentations.
Strong communication and cross-functional partnership skills.

Nice To Haves

Experience developing and scaling in-house MMM capabilities and working across custom-built and established or open-source MMM frameworks.
Experience measuring marketing’s impact on brand awareness, consideration, search, site traffic, or organic demand.
Experience calibrating or validating MMM using experiments, geo tests, holdouts, or other causal measurement approaches.
Data engineering experience, including automated analytical pipelines and productionized modeling workflows.
Experience developing analytical applications, optimization interfaces, or internal decision-support tools.
Experience with Java or other software engineering languages or frameworks.
Experience with visualization or BI platforms such as Tableau.
Experience in consumer, subscription, e-commerce, or direct-to-consumer businesses.

Responsibilities

Develop, maintain, and enhance global Marketing Mix Models measuring incremental marketing impact across channels, products, markets, and business outcomes.
Work with underlying modeling code to diagnose, modify, and extend the modeling framework.
Evaluate model specifications, methodologies, transformations, interactions, and assumptions in light of statistical performance and business context.
Develop and evaluate adstock and carryover transformations that reflect differences in how media across funnel stages influences consumer behavior.
Identify and incorporate baseline and control variables, including seasonality, promotions, pricing, product availability, macroeconomic and industry factors, and organic demand.
Diagnose model fit, stability, contribution estimates, incrementality, and issues such as multicollinearity, confounding, cannibalization, or implausible model behavior.
Develop validation approaches using holdouts, out-of-sample performance, experiments, and other incrementality evidence.
Model media’s impact on intermediate outcomes, including brand metrics and organic or direct traffic.
Identify and evaluate variables and hypotheses that improve understanding of how marketing influences consumer behavior.
Connect upper-, mid-, and lower-funnel measurement, accounting for short-term response and longer-term marketing impact.
Develop channel-level response and saturation curves to quantify diminishing marginal returns to marketing investment.
Translate MMM outputs into incremental CAC, ROI, response rates, average effectiveness, and marginal effectiveness measures.
Develop global marketing budget optimization and scenario-planning capabilities to evaluate spend levels, channel allocations, and investment strategies.
Incorporate constraints such as minimum and maximum spend, channel scalability, seasonality, and business priorities into optimization.
Evolve modeling and optimization capabilities into scalable decision-support tools for Analytics, Marketing, Media, and Finance.
Analyze the business drivers behind changes in marketing performance, including changes in media strategy and buying behavior.
Distinguish effects driven by investment levels, media efficiency, audience strategy, channel mix, market conditions, and other business factors.
Translate analytical findings into recommendations on marketing investment, channel allocation, and strategy.
Partner with Media teams to ground analytical conclusions in campaign planning, buying, and optimization practices.
Develop decision-oriented presentations and executive narratives explaining model results, performance drivers, opportunities, implications, and investment decisions.
Communicate model uncertainty, limitations, and tradeoffs to technical and non-technical stakeholders.
Partner with Data Engineering and Analytics to build reliable, scalable data pipelines for recurring MMM refreshes.
Help automate model ingestion, execution, validation, reporting, and monitoring.
Contribute to user-facing scenario-planning and optimization tools and establish documentation, QA standards, model governance, and repeatable processes.