3D Machine Learning Engineer (f/m/d)
Pubblicato il 11-10-2026 - Altro in Roma
You'll join our core 3D AI team: researchers and engineers working across the entire 3D stack: from raw data capture and geometric reconstruction to neural rendering and generative material synthesis. The team bridges academic rigor and production reality, moving fast without losing depth. Collaboration is close, hierarchy is flat, and the problems are genuinely hard.
What This Role Could Look Like This is an open call for talented people working in 3D; whether your background is in computer vision, rendering, or machine learning. We're not hiring for a fixed spec; we're looking for people who are excellent in at least one of these areas and curious about the others.
Depending on your background and interests, you could be working on:
3D Computer Vision & Reconstruction
Building the geometric backbone of our scanning pipeline: multi-camera calibration, feature-based reconstruction, structure-from-motion, and high-precision mesh optimization. Integrating learned components where they outperform classical methods.
Inverse Rendering
Developing learning-based systems that recover geometry and physically-based materials from captured imagery—NeRF variants, Gaussian splatting, differentiable rendering, material decomposition, and relighting pipelines.
Neural Rendering & Material Systems
Designing BRDF models and material representations, building diffusion-based rendering pipelines, and developing intrinsic decomposition models that separate albedo, shading, and material properties from real-world captures.
Fields of Work
Multi-camera calibration, SfM, bundle adjustment, mesh processing
Inverse rendering:
material and geometry estimation from images
Differentiable rendering and appearance decomposition
Generative 3D reconstruction: diffusion-based approaches, feed-forward networks
BRDF modeling and physically-based material synthesis
Integration of classical and learned components into production pipelines
Qualifications
Master's or PhD in Computer Science, Computer Vision, Computer Graphics, Robotics, or a related field
3+ years of hands‑on experience in at least one of the areas described above
Solid understanding of either multi-view geometry, physically-based rendering, or generative models applied to 3D (diffusion, latent representations)
Ability to move between research and production, prototyping fast and shipping clean code
Strong programming skills in Python and/or C++
Nice to Have
Experience with differentiable rendering frameworks (Mitsuba 3, nvdiffrast, PyTorch3D)
CUDA or GPU-accelerated geometry/rendering pipelines
Familiarity with structured light systems, photogrammetry, or appearance capture
Published research or open-source contributions in 3D vision, graphics, or ML
Experience with USD/MaterialX, Unreal, or real-time rendering pipelines
Benefits
Competitive salary and stock options
Visa sponsorship and relocation support
Flexible working hours and remote work policy
Participation in SIGGRAPH, CVPR, and global AI conferences
Lunch vouchers, coffee bar and gym access (Durst AG campus)
A research environment with real production impact and world-class clients
#J-18808-Ljbffr