Senior Data Scientist - (Content, Consumer)

Company Description

As the world’s pioneering local delivery platform, our mission is to deliver an amazing experience, fast, easy, and to your door. We operate in around 65 countries worldwide powered by tech, designed by people. As one of Europe’s largest tech platforms, headquartered in Berlin, Germany. Delivery Hero has been listed on the Frankfurt Stock Exchange since 2017 and is part of the MDAX stock market index. We enable creative minds to deliver solutions that create impact within our ecosystem. We move fast, take action and adapt. No matter where you're from or what you believe in, we build, we deliver, we lead. We are Delivery Hero.

Job Description

We are on the lookout for a Senior Data Scientist to join our Content tribe.

We’re building the next generation of ratings & reviews (social proof) systems from scratch — reimagining how millions of users make decisions across our platforms. This is a true greenfield space where we’re leveraging LLMs and modern NLP approaches to turn messy, real-world user content into clear, actionable signals.

We’re in the middle of rebuilding momentum and ownership of these systems, with a lot still undefined and up for grabs. This isn’t about incremental modeling — it’s about taking full ownership of data products end-to-end: shaping the problem, building the solution, and making it work reliably in production in a fast-moving, high-impact environment.

Your Mission

• You’ll own and scale social proof solutions end-to-end, ensuring high quality, reliability, and coverage across languages, platforms, and use cases, while proactively managing drift, miscalibration, and data quality issues.
• You’ll drive the product and roadmap through problem discovery, identifying high-impact opportunities, quantifying business value, and translating them into concrete DS/ML initiatives.
• You’ll take ML and LLM solutions from prototype to production, building robust, scalable systems and collaborating closely with backend and data engineering on architecture and data flows.
• You'll establish LLM evaluation infrastructure, building offline evaluation pipelines and annotation processes that allow the team to make confident decisions about prompt changes, model switches, and system iterations.
• You’ll establish statistical rigor in decision-making, designing and owning A/B tests and quasi-experiments, and ensuring credible impact measurement aligned with real business outcomes.
• You’ll define and operationalize meaningful metrics, ensuring evaluation reflects true business value rather than misleading proxies.
• You’ll raise the bar for data science in the team, driving best practices, mentoring others, and contributing to a culture of ownership, pragmatism, and technical excellence.

Qualifications NLP & LLM Domain Expertise

• You have hands-on experience with NLP and LLM-based systems in user-generated, noisy, multilingual contexts — with clear judgment on when LLMs add value, when to prompt-engineer vs. fine-tune, and how to optimize prompts systematically at scale. You can reason empirically about cost, latency, and quality tradeoffs across model providers and make principled model selection decisions.

End-to-End Ownership & Product Execution

• You have experience owning data science solutions end-to-end, from problem definition to production, iteration, and continuous improvement.
• You are comfortable owning production systems, not just building models, and take responsibility for reliability, performance, and outcomes.
• You write production-grade code in Python and SQL, and are familiar with ML lifecycle practices, orchestration, monitoring, and modern engineering standards (e.g., CI/CD, version control).
• You are familiar with LLM-specific observability: tracing chained LLM calls, monitoring token usage and cost, and instrumenting multi-step pipelines for reliability and debugging.
• You can translate ambiguous b