Generative AI Research Scientist — 3D Rendering & Vision

Athlence; Zürich; Hybrid; CHF 140,000 - 210,000; Full time

Benefits offered by this job

Access to proprietary multi-camera, in

Small, highly technical team

Job summary

Athlence is seeking a Research Scientist to develop the generative modeling technology behind our rendering pipeline. You will focus on creating high-quality, temporally coherent renderings from 3D and 4D representations while preserving geometry and multi-view consistency.

The role involves working with diffusion, flow-based and video generation approaches, adapting models to Athlence's multi-view data, and collaborating with the 3D reconstruction team to integrate generative ideas into

Qualifications

• Strong practical experience with modern generative models, particularly diffusion or flow-based models.
• A rigorous understanding of diffusion models, noise schedules, flow matching, or related methods.
• Hands-on experience training, fine-tuning, adapting, or distilling 2D, video, or 3D generative models.
• Strong Python and PyTorch skills, with experience building training and evaluation pipelines.
• Good foundations in computer vision and 3D, including familiarity with camera models and basic multi-view geometry.
• Experience designing experiments, analyzing model behavior, and investigating failure modes.
• Ability to take research ideas from an initial hypothesis through implementation, experimentation, and evaluation.
• Ability to work independently and communicate technical results and trade-offs clearly.

Responsibilities

• Research and develop generative models for high-quality, temporally consistent rendering from 3D and 4D scene representations.
• Explore diffusion, flow matching, rectified flow, video generation, and related generative modeling approaches.
• Adapt and fine-tune large-scale 2D, video, and 3D generative models to Athlence's data.
• Develop conditioning mechanisms that incorporate geometry, camera information, temporal context, and multi-view observations.
• Develop evaluation metrics and benchmarks that capture perceptual quality and temporal/multi-view consistency beyond conventional pixel-based metrics.

Skills

Generative models

Diffusion

PyTorch

Python

3D vision

Multi-view geometry

Experiment design

Independent work

Tools

PyTorch

Python

Job description

Athlence is seeking a Research Scientist to develop the generative modeling technology behind our rendering pipeline. You will focus on creating high-quality, temporally coherent renderings from 3D and 4D representations while preserving geometry and multi-view consistency.

The role involves working with diffusion, flow-based and video generation approaches, adapting models to Athlence's multi-view data, and collaborating with the 3D reconstruction team to integrate generative ideas into