Senior Data Scientist (d/f/m)

<p><span><b>Kleinanzeigen</b> is the leading online classifieds market in Germany. An average of more than 50 million ads are available in numerous categories - from children's supplies to electronics to real estate. With more than 36 million users per month, Kleinanzeigen has the widest reach of all online selling platforms in the country. Most of the items traded on Kleinanzeigen are second-hand. In this way, users make an active contribution to sustainability. The Kleinanzeigen market allows companies the opportunity to easily offer their services online. Kleinanzeigen was launched in September 2009 as eBay Kleinanzeigen. Since June 2021, the company has been part of Adevinta, a leading global provider of online classified ads. In May 2023, the name was changed to Kleinanzeigen.</span></p><p></p><p><span><span>Kleinanzeigen is</span></span> part of Adevinta: a global online classifieds specialist and sustainability leader with 25+ products in 10 countries.</p><p></p><p></p><h1><b><span>What you’ll do</span> ​&amp; Who you are</b></h1><p></p><p></p><p><span>We are looking for a Senior Data Scientist to join our mission to make our platform an even safer place to trade. You will be responsible for designing, building, and continuously enhancing production-grade, end-to-end machine learning models that detect fraud and assess user risk in the Trust and Safety domain. You will be part of a cross-functional business area composed of multiple teams including experts from Product, Customer Service, Analytics, Data and Engineering. Together, you’ll tackle one of the most meaningful challenges in online platforms: building trust at scale.</span></p><p><span>This is your opportunity to improve the experience of millions of users and have an impact by building a platform that enables sustainable trade for <span>everyone.  </span></span></p><p></p><p><span>Your role:</span></p><ul><li><p><span>Understand fraud patterns, user trust needs and identify where Machine Learning can bring the greatest impact.</span></p></li><li><p><span>Develop ML models from scratch or fine-tune existing ones for fraud detection and behavioural analytics</span></p></li><li><p><span>Train and test deep learning models.</span></p></li><li><p><span>Work as part of an agile cross-functional development team with a “win together, lose together” mindset, having end-to-end responsibility from design and development to deployment, monitoring, and maintenance in production.</span></p></li><li><p><span>Engineer and select features from large, complex datasets to improve model accuracy and robustness.</span></p></li><li><p><span>Monitor and evaluate ML models in production, conduct model experiments, comparing variants and identifying improvement and retraining needs.</span></p></li><li><p><span>Ensure data and model quality, integrity, and reproducibility in production environments.</span></p></li><li><p><span>Share your knowledge, evolve best practices with your colleagues to boost machine learning at Kleinanzeigen strengthening our ML community.</span></p></li><li><p><span>Proactively identify opportunities to apply ML for fraud detection and increased user trust.</span></p></li><li><p><span>Promote ethical AI use, ensuring fairness, transparency, and accountability in all models developed.</span></p></li></ul><p></p><p><span>Qualifications</span></p><ul><li><p><span>Master’s degree in computer science, data science, statistics, mathematics or related field (or equivalent experience)</span></p></li><li><p><span>At least 5+ years of proven experience applying ML and deep learning methods to build and deploy production-grade models (e.g., XGBoost, Random Forests, Logistic Regression, Neural Networks, Transformers) </span>ideally in fraud detection or Trust &amp; Safety domain, e<span>nsuring quality and robustness of data science outputs.</span></p></li><li><p><span>Strong proficiency in Python and ML libraries (e.g., scikit-learn, PyTorch, XGBoost), with proven experience applying classical ML to structured and time series data, including feature engineering, model evaluation (e.g., precision/recall, AUC), and deploying scalable models (e.g., XGBoost, Random Forests, Logistic Regression) to production.</span></p></li><li><p><span>Solid understanding of ML/DS best practices, including model validation, A/B testing, feature engineering, and pipeline management.</span></p></li><li><p><span>Practical experience with Generative AI and Large Language Models (LLMs) for tasks such as classification, summarization, or risk signal extraction from unstructured text, with a clear understanding of evaluation, prompt design, and ethical considerations in production use.</span></p></li><li><p><span>Familiarity with cloud-based environments (e.g., AWS) and production ML tools (e.g., SageMaker, Airflow, MLflow).</span></p></li><li><p><span>Experience working in Agile teams with modern DevOps/dataops practices.</span></p></li><li><p><span>True team player mentality