Staff Data Scientist - Global Search, Consumer at Delivery Hero in Berlin
- Company: Delivery Hero
- Location: Berlin, de
- Job type: full time
- Workplace: onsite
- Posted: 2026-11-19
All open roles at Delivery Hero
Job description
Deep analysis. Smarter systems. Real users. As a Staff Data Scientist, you’ll own the deep learning ranking models behind the search services that power every Delivery Hero platform. You’ll also lead our move to agentic ML research, using LLM coding agents to run hundreds of overnight experiments and turn the strongest signals into ranking gains in production. Our search functionality spans more than 60 countries and 35 languages, facilitating over 80 million searches daily across four continents. The ranking systems you build will directly shape what millions of customers see every time they open the app. At Delivery Hero, you’ll shape the global consumer experience for millions of users. Your work will have a direct impact on how we attract and retain customers, creating data-driven, personalized interactions that keep them coming back. As part of our Consumer Team, you’ll enhance customer satisfaction and drive global growth and profitability through innovative projects. Act as the technical leader for search ranking across the domain, owning model and architecture design for deep neural ranking models (DCN-V2, MMoE, Two-Tower) from offline experimentation through production. Lead agentic ML research and drive its adoption across the domain: use LLM coding agents (e.g. Claude Code, Gemini) to run overnight experiment pipelines on features and LTR architectures, and turn the strongest signals into production gains. Improve ranker quality through feature engineering and model architecture work, drawing on ranking signals, feature stores and embedding-based retrieval, and turning the latest research into production-grade systems. Set the standards for production model health across the domain’s squads (drift, latency, feature pipeline integrity) and drive their adoption. Work with Product and Engineering leads to set the vision, mission and goals for the search ranking squads, and present results to stakeholders in clear, simple terms. Mentor junior and senior data scientists, review and audit their work to ensure quality, and contribute to hiring as a bar raiser. A Master’s degree in Computer Science, Mathematics, Physics or a related quantitative field (or a Bachelor’s with 6+ years of work experience), plus 4+ years as a Data Scientist or Machine Learning Engineer applying ML in high-traffic production environments. Production-proven experience with deep learning ranking architectures (DCN-V2, MMoE, Two-Tower), including multi-task learning, cross-feature interactions and embedding optimization at scale, plus a solid foundation in LTR methods (pointwise, pairwise, listwise), offline metrics (NDCG, MRR) and bridging offline metrics to online A/B outcomes. Proficiency with LLM coding agents and agentic CLI tools (e.g. Claude Code, Gemini) for autonomous experiment generation, architecture prototyping and rapid iteration, familiarity with the auto-research paradigm, and comfort reviewing large volumes of generated experiment results. Expert Python across the ML ecosystem (PyTorch, TensorFlow, scikit-learn), working knowledge of SQL (dbt), GCP or AWS and big-data processing (PySpark, Scala), and hands-on MLOps across the full lifecycle: feature stores, vector databases, model registry, Metaflow, CI/CD for ML, experiment tracking, A/B frameworks, low-latency deployment and production monitoring. Track record of leading data science projects in highly ambiguous, complex problem spaces with long-term impact on a product or architecture, making the right trade-offs. Experience setting technical standards across multiple teams, building consensus among stakeholders with differing views, and explaining model trade-offs to technical and non-technical audiences. Ensuring you and all our Heroes are looked after, happy, and healthy is always on the menu. Because if you’re in good shape, then we’re in good shape. Make the most of our  hybrid working model  and join the team for face-to-face connection and collaboration in our be
Staff Data Scientist - Global Search, Consumer on JobPost.