Lead Data Scientist

<p>&nbsp;</p> <h2><strong>Hello, let’s meet!</strong></h2> <p><strong>Who We Are</strong></p> <p>While Xebia is a global tech company, our journey in CEE started with two Polish companies – PGS Software, known for world-class cloud and software solutions, and GetInData, a pioneer in Big Data. Today, we’re a team of 1,000+ experts delivering top-notch work across cloud, data, and software. And we’re just getting started.</p> <p><strong>What We Do</strong></p> <p>We work on projects that matter – and that make a difference. From fintech and e-commerce to aviation, logistics, media, and fashion, we help our clients build scalable platforms, data and AI solutions, and cutting-edge applications to shape the future of tech. Our clients include McLaren, Aviva, Deloitte, Spotify, Disney, ING, UPS, Tesco, Truecaller, AllSaints, Volotea, Schmitz Cargobull, Allegro, InPost, and many, many more.</p> <p>We value smart tech, real ownership, and continuous growth. We use modern, open-source stacks, and we’re proud to be trusted partners of Databricks, dbt, Snowflake, Azure, GCP, and AWS. Fun fact: we were the first AWS Premier Partner in Poland!</p> <p><strong>Beyond Projects</strong></p> <p>What makes Xebia special? Our community. We support tech communities, organize meetups (Software Talks, Data Tech Talks), and have a culture that actively support your growth via Guilds, Labs, and personal development budgets — for both tech and soft skills. It’s not just a job. It’s a place to grow.</p> <p><strong>What sets us apart?&nbsp;</strong></p> <p><strong>Our mindset. Our vibe. Our people. And while that’s hard to capture in text – come visit us and see for yourself.</strong></p> <p>&nbsp;</p> <h2><strong>You will be:</strong></h2> <ul> <li>designing and developing statistical models for property price adjustments across time, location, quality, and condition,</li> <li>building spatial algorithms (adaptive heatmaps, geographic clustering, polygon-based property search) to capture local market dynamics,&nbsp;</li> <li>implementing comparable property recommendation with feature engineering across different property types,&nbsp;</li> <li>developing market analysis pipelines with solid diagnostics: trend fitting, outlier detection, goodness-of-fit metrics,&nbsp;</li> <li>integrating LLM-based classification services for document and property analysis,&nbsp;</li> <li>exposing model outputs through production API endpoints and working with frontend engineers on data contracts,&nbsp;</li> <li>debugging models in production: edge cases, numerical issues, data quality problems.</li> </ul> <h2 data-pm-slice="1 1 []"><strong>Your profile:</strong></h2> <ul> <li>solid statistics background: regression, GAMs, mixed/random effects, link functions, robust estimation, outlier handling,</li> <li>proficiency in Python and the data science stack: NumPy, Pandas, statsmodels, SciPy, scikit-learn,&nbsp;</li> <li>experience building and maintaining production APIs with FastAPI and Pydantic,&nbsp;</li> <li>comfortable working with PostgreSQL and SQLAlchemy,&nbsp;</li> <li>familiar with containerized environments (Docker, Kubernetes, GCP),&nbsp;</li> <li>able to turn domain requirements into quantitative solutions and communicate trade-offs,&nbsp;</li> <li>good command of English (spoken and written),&nbsp;</li> <li>familiarity with basic statistical concepts (e.g., Bayes’ rule, linear regression, maximum likelihood estimation,</li> <li>practical experience using AI-powered assistants (e.g. Claude Code, GitHub Copilot, Cursor) to improve productivity, quality, or decision-making in software delivery.</li> </ul> <p><strong>Work from the European Union region and a work permit are required.</strong></p> <h2><strong>Nice to have:</strong></h2> <ul> <li>geospatial data and libraries (GeoPandas, Shapely, H3, GeoAlchemy2),</li> <li>GAM libraries (PyGAM), JAX, or TensorFlow Probability,&nbsp;</li> <li>task queues and async workflows (Celery, Redis),&nbsp;</li> <li>observability tooling (OpenTelemetry),&nbsp;</li> <li>ML pipeline frameworks (Kedro),&nbsp;</li> <li>data validation and property-based testing (Pandera, Hypothesis, TestContainers),&nbsp;</li> <li>R integration (rpy2),</li> <li>LLM integrations (Google Gemini or similar),</li> <li>frontend awareness (React, TypeScript),</li> <li>real estate data, valuation methodology, or appraisal workflows.</li> </ul> <h2><strong>Recruitment Process:</strong></h2> <p><strong>CV</strong> review –<strong> HR</strong> call – <strong>Interview</strong> – <strong>Client </strong>Interview – <strong>Decision</strong></p> <p>&nbsp;</p>