About Athlence
Athlence is building technology to capture live sports events in 4D and render them from novel viewpoints to create immersive, broadcast-quality experiences. Our technology combines synchronized multi-camera video, 3D reconstruction, and generative models to build highly realistic representations of dynamic sports scenes.
We are a Zurich-based deep-tech startup working at the intersection of computer vision, machine learning, and high-performance engineering. We develop and test our technology in real-world professional sports environments, where reconstruction quality, robustness, and system performance all matter.
About the role
We are looking for a Research Scientist to develop the generative modeling technology behind Athlence's rendering pipeline.
The focus of this role is on developing generative models to improve the visual quality of reconstructed scenes while preserving geometry, multi-view consistency, and temporal coherence. You will work with diffusion, flow-based, video, and other generative architectures, developing methods that incorporate geometry, camera information, multi-view observations, and temporal context.
The role sits at the intersection of generative modeling and 3D vision. You will work closely with the 3D reconstruction team to connect geometric representations with generative models and develop methods that can operate reliably on real-world multi-camera captures.
What you will be doing
- 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 multi-view and temporal data
- Develop conditioning mechanisms that incorporate geometry, camera information, temporal context, and multi-view observations
- Explore feed-forward architectures and 3D/4D representations that connect sparse multi-view inputs directly to renderable scene representations
- Design and run experiments to understand the trade-offs between perceptual quality, geometric consistency, temporal stability, latency, and compute
- Develop evaluation metrics and benchmarks that capture perceptual quality and temporal/multi-view consistency beyond conventional pixel-based metrics
- Build training, evaluation, and inference pipelines for large-scale generative models
- Define and improve the data distribution used to train generative models, including dataset curation, filtering, and preprocessing
- Collaborate closely with the 3D reconstruction and systems teams to integrate generative models into the broader rendering pipeline
What you must have
- Strong practical experience with modern generative models, particularly diffusion or flow-based models
- A rigorous understanding of the principles behind diffusion models, noise schedules, flow matching, or related generative modeling 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
Nice to have
- Experience with large-scale distributed training using technologies such as FSDP, DeepSpeed, or similar
- Experience with video generation, temporal modeling, or multi-view generative models
- Experience with novel-view synthesis, neural rendering, Gaussian Splatting, NeRFs, or other 3D representations
- Experience conditioning generative models on geometry, depth, camera parameters, or other spatial information
- Experience optimizing generative models for inference latency, memory usage, or throughput
- Publications at leading computer vision or machine learning venues such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, or ICML
- Open-source work or impactful research projects demonstrating practical generative modeling experience
What we offer
- Access to unique, proprietary multi-camera sports data captured in real-world environments
- The opportunity to work on challenging generative modeling and 3D vision problems where research ideas are evaluated against real-world constraints
- High ownership across the full research cycle, from research exploration and experimentation to integration and deployment
- A small, highly technical team where you can directly influence the research direction and systems we build
How to apply
Please send your CV and a one-page note about the most interesting diffusion or generative model you fine-tuned or contributed to, the base you chose, the data you curated, what worked, what did not. GitHub, HuggingFace checkpoint, or a project link welcomed.
- Send to
- hiring@athlencesports.com
- Subject line
Diffusion Model — [Your Name]