About Vision Automation
As a key player in the digital transformation of interior spaces, we're building innovative solutions to bridge the gap between online design and real-world manufacturing. Our AI-powered tools aim to revolutionize the way architects and designers work with 2D floorplans, converting them into 3D layouts to streamline design, quoting, and production workflows.
Your Role
We're seeking an experienced Machine Learning Engineer to lead the development of a system that can analyze floorplan images (PDFs, DWGs, etc.) and convert them into 3D geometry - walls, doors, windows, and more - ready for our CPQ engine.
Key Responsibilities
* Design and train deep learning models to extract spatial and semantic information from 2D floorplans (images or vector files).
* Develop pipelines to convert detected geometry into structured 3D models (e.g., wall objects, door/window placement).
* Work with vector data (DXF/DWG), PDFs, or raster images to detect key architectural features.
* Collaborate with CAD and backend engineers to translate AI output into parametric geometry.
* Optimize models for speed, accuracy, and usability in real-world production environments.
Requirements
We're looking for an expert in computer vision and machine learning to join our team. You should have:
* Strong experience with deep learning frameworks (PyTorch, TensorFlow) and vision models (YOLO, UNet, Detectron, etc.).
* Experience in computer vision or document/image parsing.
* Understanding of geometry-based learning and spatial context.
* Ability to translate model output into geometric representations.
Benefits
You'll be part of a dynamic team working on cutting-edge technology. We offer competitive compensation and opportunities for professional growth and development.