> Markdown version of [/jobs/ext/2211488-data-scientist-martech-measurement-optimization](https://www.wearedevelopers.com/jobs/ext/2211488-data-scientist-martech-measurement-optimization). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist - MarTech (Measurement & Optimization) - **Company:** Glovo - **Location:** United States (Remote available) - **Contract:** Permanent contract - **Skills:** Data Analysis, BigQuery, Python (Programming Language), Modular Design, Backtesting, Standard Sql, Software Deployment, Strategies of Testing, Model-Driven Development, Large Language Models, Model Validation, Software Version Control - **Published:** August 24, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/pecdjheihx ## About the Role This role requires solid foundations in causal inference and modeling, combined with the ability to communicate clearly with technical and non-technical stakeholders and translate marketing problems into reliable, production-grade solutions., Statistical, Causal & Predictive Foundations Solid foundation in experimentation, causal inference, time-series, and predictive modeling. Experience applying these methods in real-world settings with noisy or biased data. Working Effectively Under Ambiguity * Make sound progress on partially-defined problems, escalating when blocked * Provide reasoned analyses under uncertainty * Recognize trade-offs between conflicting methodologies and signals Feature & Model Ownership Track record of owning models and features from problem definition * modeling approach * production * adoption, with senior input on more open-ended initiatives. MarTech Domain Exposure Working understanding of attribution, digital and offline channels, performance marketing, bidding, and budget allocation. Familiarity with incrementality, diminishing returns, and cross-channel interactions. Stakeholder Communication * Communicate statistical concepts to non-technical stakeholders * Present model results clearly and discuss limitations honestly * Build trust through reliable, well-documented work Engineering & Production Skills Strong Python and SQL skills (e.g., BigQuery). Experience with modular design, testing, version control, and modern data/ML stacks. Exposure to agentic workflows (LLM-driven or tool-using agents) is a plus. Pragmatic Approach Familiarity with methods such as uplift modeling, MMM, quasi-experiments, and survival models. Ability to apply established methods to deliver real business impact. ## Description The MarTech Data Science team drives performance marketing efficiency through advanced measurement, optimization, and scalable modeling. We operate in a highly complex and ambiguous environment where: * Ground truth is often unobservable (incrementality vs attribution) * Clean experimentation is not always feasible * Decisions must be made under uncertainty with imperfect data We build solutions for budget allocation, incrementality measurement, and bidding, enabling the business to invest each euro where it generates the highest impact., We are looking for a Data Scientist to own models and features end-to-end within larger MarTech initiatives, and contribute to the team's measurement and optimization solutions. Operating at a global level, you will design solutions that serve the entire Delivery Hero portfolio, including brands like Glovo, Talabat, and PedidosYa. You will work autonomously on well-defined problems and collaborate closely with senior team members on more ambiguous ones., * Take ownership of models and features inside larger initiatives, from data exploration to production deployment * Contribute to defining success metrics and modeling approaches, with senior guidance on more ambiguous problem framings * Balance methodological rigor with business constraints and timelines Contribute to decision frameworks under ambiguity * Help translate marketing questions into structured, model-driven analyses * Operate in environments where experimentation is limited or infeasible, applying established methods across MMM, experiments, and observational analysis * Make and document assumptions explicitly, and flag their impact on decisions Support decision-making under uncertainty * Provide clear analyses despite imperfect measurement, articulating trade-offs and limitations * Identify conflicting signals (e.g., attribution vs incrementality vs MMM) and discuss them with senior team members * Ensure outputs are actionable and aligned with real business constraints (budget caps, pacing, channel dependencies) Apply methodological rigor and contribute to validation * Contribute to and apply frameworks across MMM, incrementality testing (geo experiments, synthetic control), bidding, and/or LTV * Apply validation strategies in the absence of ground truth (cross-method validation, backtesting, sensitivity analysis) * Follow team standards for statistical rigor, interpretability, and reproducibility * Participate in knowledge sharing within the chapter and team Communicate effectively with stakeholders * Translate modeling outputs into clear narratives for non-technical stakeholders * Communicate with squad-level stakeholders, adapting abstraction level appropriately * Address questions on model outputs with appropriate context and honesty about limitations Build production-grade systems * Develop reliable, maintainable solutions with good standards in testing, monitoring, documentation, and reproducibility * Work closely with Engineering and Product to deploy and improve systems * Ensure long-term usability of models as decision products, not just analyses ## Related Videos - [Data Science in Retail](https://www.wearedevelopers.com/videos/586-data-science-in-retail) - [How to implement convenient Python bindings to C++](https://www.wearedevelopers.com/videos/618-how-to-implement-convenient-python-bindings-to-c) - [How building an industry DBMS differs from building a research one](https://www.wearedevelopers.com/videos/768-how-building-an-industry-dbms-differs-from-building-a-research-one) - [Making Data Warehouses fast. A developer's story.](https://www.wearedevelopers.com/videos/302-making-data-warehouses-fast-a-developer-s-story) - [Data Governance in the Era of AI](https://www.wearedevelopers.com/videos/1622-data-governance-in-the-era-of-ai) - [Developer Experience, Platform Engineering and AI powered Apps](https://www.wearedevelopers.com/videos/990-developer-experience-platform-engineering-and-ai-powered-apps) ## Related Articles - [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production) - [The Biggest German Tech Companies](https://www.wearedevelopers.com/magazine/424-the-biggest-german-tech-companies) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Best Companies to work for in London: Top 25 Companies in 2023](https://www.wearedevelopers.com/magazine/187-best-companies-to-work-for-in-london-top-25-companies-in-2023) - [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it) - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models)