3D/4D Reconstruction Scientist — Dynamic Scenes & Novel Views

Athlence; Zürich; Hybrid; CHF 130,000 - 180,000; Full time

Job summary

Athlence is seeking a Research Scientist to advance the 3D reconstruction technology behind its capture and rendering pipeline. The role focuses on reconstructing fast-moving dynamic scenes from sparse multi-view inputs and rendering them from novel viewpoints with high visual fidelity and temporal consistency.

You will work with 3D/4D Gaussian Splatting and feed-forward 3D models, adapting methods and developing new approaches for robust, photorealistic reconstruction.

Qualifications

• Strong hands-on experience in deep learning and computer vision
• Strong foundations in multi-view geometry, 3D reconstruction, and camera calibration
• Deep expertise in 3D/4D Gaussian Splatting, feed-forward 3D reconstruction, neural rendering, or similar
• Strong Python and PyTorch skills, with experience building training/evaluation pipelines
• Experience designing experiments and analyzing model behavior
• Ability to work autonomously in a fast-paced, highly technical team

Responsibilities

• Research and develop 3D/4D Gaussian Splatting and modern feed-forward 3D models for high-quality dynamic scene reconstruction and novel-view synthesis
• Develop methods to reconstruct dynamic scenes from sparse multi-view observations while preserving geometry, appearance, and temporal consistency
• Explore model architectures, scene representations, training objectives, and approaches to improve fidelity, latency, and compute efficiency
• Design and run rigorous experiments to understand model behavior, failure modes, and trade-offs between fidelity, geometry, runtime
• Develop evaluation metrics and benchmarks for reconstruction quality across geometry, appearance, and novel-view rendering
• Build reliable training, evaluation, and inference pipelines for 3D reconstruction models
• Contribute to data pipeline processing, filtering, and curating large-scale multi-camera datasets
• Collaborate with generative modeling and hardware engineers to connect reconstruction methods with capture infrastructure

Skills

Deep learning

Computer vision

Multi-view geometry

3D reconstruction

Python

PyTorch

Experiment design

Autonomy

Scientific communication

Job description

Athlence is seeking a Research Scientist to advance the 3D reconstruction technology behind its capture and rendering pipeline. The role focuses on reconstructing fast-moving dynamic scenes from sparse multi-view inputs and rendering them from novel viewpoints with high visual fidelity and temporal consistency.

You will work with 3D/4D Gaussian Splatting and feed-forward 3D models, adapting methods and developing new approaches for robust, photorealistic reconstruction.