Data Scientist at Fuchs & Eule

Additional Description of Tasks

    Developed an automated building energy modeling pipeline leveraging 3D data to predict building components (e.g., roofs, walls, windows), reducing manual model creation time from 3–8 hours to 3-8 seconds

    Integrated physics-based simulations via a kernel endpoint to estimate building energetic states and financial KPIs, eliminating the need for manual post-processing

    Delivered a scalable in-use product that streamlined analysts' workflows, combined data science with energy simulation, and significantly accelerated energy efficiency assessments for building portfolios

    Collaborate daily with energy consultants, analysts, and software engineers to align technical solutions with actual practical needs, ensuring the products I build deliver real workflow improvements and value

    Built a document processing and RAG system that ingests building documentation (plans, specifications, manuals) through an OCR and chunking pipeline, stores them as semantic embeddings in a vector database, and enables natural language querying over internal and external documents

  • Location: Berlin, Germany
  • Start Date: May 2025
  • End Date: Present
  • List of Relevant Technologies Used: Python, Data Science, Computational Geometry, API Development, RAGs, LLMs, Optimization, 3D Modeling