Zürich Metropolitan Area
Research Engineer working at the intersection of machine learning and computer graphics, with industry and academic research experience in neural rendering, real-time graphics, and generative models. Current focus: neural rendering and neural scene representations (NeRFs, Gaussian splatting, etc.), differentiable rendering, real-time graphics, and generative models (diffusion models, VAEs, etc.). Prior research on Monte Carlo path tracing, global illumination, the many-lights problem, and reinforcement learning for light transport at KU Leuven and Disney Research, with peer-reviewed publications in the field. Core expertise: • Neural rendering, real-time rendering, neural radiance fields (NeRF), 3D Gaussian splatting (3DGS) • Generative models: diffusion, VAEs, latent representations • Monte Carlo methods, path tracing, global illumination, many-lights problem • Deep learning research and production: PyTorch, CUDA, Python, C++
Research at the intersection of machine learning and computer graphics, with a focus on real-time neural rendering and generative 3D scene synthesis. Selected work: • Real-time Rendering with a Neural Irradiance Volume — first author, Computer Graphics Forum (Eurographics), 2026 • Real-time Neural Rendering of Dynamic Light Fields — first author, Computer Graphics Forum (Eurographics), 2024 • DreamAnywhere: Object-Centric Panoramic 3D Scene Generation — WACV 2026 • Effect-based Multi-viewer Caching for Cloud-native Rendering — SIGGRAPH (Journal Track), 2023 Keywords: neural rendering, real-time rendering, neural radiance fields, light fields, 3D scene generation, diffusion models, generative 3D, global illumination, computer graphics, PyTorch, CUDA.
Machine learning and graphics research.
Researching the use of machine learning algorithms to solve global illumination problems. Focus on reinforcement learning and neural representations.
Full stack development on the DataCamp platform.