Senior Applied Scientist (all genders)

Role: Partner Tech builds the products, tools, and insights that help Zalando partners grow with confidence. Within Assortment, Steering & Data Insights (ASDI), we develop data products and decision systems that improve assortment composition, in-season steering, demand understanding, partner performance insights, and commercial automation across our wholesale and Partner Platform businesses. As a Senior Applied Scientist, you will focus primarily on measuring the impact of ASDI products while also supporting selected strategic Partner Tech-wide initiatives where rigorous evaluation is critical. You will design experiments where possible and robust observational studies when they are not, helping us understand the incremental effect of product, algorithmic, and policy changes on outcomes such as GMV, profitability, and operational efficiency. Working closely with Product, Engineering, Analytics, Applied Science and business stakeholders, you will turn ambiguous questions into clear evaluation strategies, reliable evidence, and better product decisions. Responsibilities: - Lead impact measurement for ASDI products and strategic Partner Tech initiatives. You will own the experimentation charter and work with cross-functional teams to define hypotheses, estimands, guardrails, and success metrics for initiatives in ASDI and broader high-priority Partner Tech topics. - Develop state-of-the-art machine learning and econometric models. You will design and develop models for observational studies to estimate the incremental effect of products, algorithmic and recommendations across the product area, thereby optimizing our recommendations and products. - Choose the right causal design. Use randomized experiments where feasible and quasi-experimental methods when not, balancing scientific rigor with practical constraints. - Communicate evidence into decisions. Effectively communicate findings, uncertainty, and trade-offs to technical and non-technical audiences, helping shape rollouts, prioritization, and investment choices. - Build trusted, extensible KPI frameworks. Design and develop robust and extensible KPI frameworks to enable evaluation and prioritization of multiple products in the domain. - Raise the bar for measurement. Keep the team up-to-date with the latest research in relevant fields like causal machine learning, econometrics, and optimization. Help define best practices for experimentation and observational causal inference, support peer reviews, and mentor colleagues. Qualifications: - PhD in Economics, Econometrics, Statistics, Causal Inference, or Causal Machine Learning. - At least 2 years of industry experience in data science with focus on experimentation and causal inference, and have used these methods to evaluate products, algorithms, recommendations, or interventions in complex, data-rich environments. - Deep expertise in experimentation and causal inference, including panel data methods, causal inference under unconfoundedness, and doubly robust methods. - Ability to independently drive a scientific workstream, develop an applied research agenda, and translate research into actionable insights at scale. - Fluent coding in Python and SQL, comfortable with large datasets and modern analytical platforms such as Spark or Databricks. - Clear communication to diverse audiences, connecting scientific insights to business impact, and helping others through mentoring, peer review, or knowledge sharing. What We Offer: - 27 days of holiday a year to start for full-time employees (+1 day for every calendar year up to 30 days) - 2 paid volunteering days a year - Employee shares programme - 40% off fashion and beauty products sold and shipped by Zalando, 30% off Lounge by Zalando, and discounts from external partners - Relocation assistance available (subject to prior agreement) - Family services, including counselling and support - Health and wellbeing options (including Wellhub) - Mental health support and coaching available - Drive your development through our training platform and biannual peer-to-peer review