Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Expert

Experience required

5 years minimum

Working hours

Regular working hours

Job source

www.juju.com

Tech stack

3D Scanning Computer Vision C++ (Programming Language) Nvidia CUDA Python (Programming Language) Machine Learning NeRF (Neural Radiance Fields) Pytorch Production Code Stable Diffusion

Job description

• Diffusion and video generation models for realistic, controllable sensor data
• Generation conditioned on scene layout, camera pose, actors and trajectories
• Temporally consistent, multi-camera video
• Adding new scenarios, weather and lighting to real-world logs
• Combining generative models with 3D reconstruction
• Scaling training and inference of large models for production

Requirements

• 5+ years building and shipping ML or computer vision systems
• Strong hands-on experience with diffusion and video models (latent/video diffusion, DiTs)
• Experience training and fine-tuning large models
• Python and PyTorch
• A track record of turning research into production code
• Bonus: 3DGS/NeRF, world models, multi-view consistent generation, distillation and efficient sampling, C++/CUDA, AV or robotics data, and publications at CVPR, NeurIPS, ICLR, ICML or similar.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.juju.com

Prepare application

• Draft this with your agent
• Open in Claude
• Open in ChatGPT
• Copy prompt