3 months ago
Munich, GermanyStaff+
Responsibilities
- Design and optimize machine learning and deep learning models for 3D point cloud filtering, denoising, registration, and surface reconstruction.
- Own 3D data pipelines from preprocessing and augmentation through model adaptation and evaluation against ground-truth geometry.
- Integrate 3D machine learning solutions into existing workflows and products in collaboration with AI researchers, software engineers, and product designers.
- Adapt state-of-the-art 3D deep learning methods, including point-based, sparse voxel or convolutional, graph-based, transformer-based, and diffusion-based approaches, for production use.
- Build scalable and reproducible training pipelines for large 3D datasets.
- Analyze geometric and perceptual quality metrics to improve model performance and raise the team’s expertise in 3D machine learning.
Requirements
- MS or PhD in computer vision, machine learning, computer science, or a related field, or equivalent practical experience.
- 5–7+ years of hands-on experience applying machine learning and deep learning to point cloud processing, filtering, registration, or surface reconstruction.
- Strong theoretical grounding in machine learning, deep learning, geometry, linear algebra, and optimization.
- Familiarity with point cloud-specific architectures, including PointNet++, sparse convolutional networks, graph neural networks, and transformer- or diffusion-based 3D models.
- Strong Python skills and hands-on experience with PyTorch, TensorFlow, and Scikit-learn.
- Fluent English communication skills for cross-functional collaboration.
- Preferred qualifications include computer graphics and GPU programming experience; experience with NeRF, Gaussian splatting, or signed distance functions; familiarity with ML experimentation and orchestration tools; relevant publications or open-source projects; experience with C++ and 3D libraries; and Linux experience.
Benefits
- 30 days of paid time off per year.
- Subsidized access to EGYM Wellpass fitness and wellness facilities.
- Deutschlandticket subsidy for public transportation.
- Flexible working hours and a hybrid work setup.
- Full visa and relocation support for international candidates.
- Bike leasing through JobRad.
- Competitive compensation package.
- Employee referral bonus.
- Financial support for local language classes.
Categories
About NavVis
NavVis builds reality-capture hardware and software used to create photorealistic digital twins of buildings and factories. Its portfolio includes the NavVis VLX wearable mobile laser scanner and the IVION cloud platform for processing and sharing spatial data, sold to surveying, AEC, and manufacturing customers. Founded in 2013 and headquartered in Munich with offices in the US, UK, and China, the company is privately held and serves a global customer base.