Vision Engineer – Synthetic 3D Data (human)

The role

You will build scalable simulation and data generation pipelines and develop World Action Models. You will work on scene simulation, domain randomization, 3D inpainting, and generative world models for humanoid and collaborative robots.

What you will do

• Conception and construction of generated 3D scenes from real-world recordings
• Development of systematic randomization strategies for domain randomization
• Development of methods for 3D inpainting and scene editing
• Use of modern simulation environments and validation of real humanoid and collaborative robots
• Design and fine-tuning of generative world models
• Work closely with AI, perception, control, and manipulation teams
• Define requirements, integrate sensor models, and develop diagnostic tools
• Create documentation and support CI/CD processes

Required qualifications

• Master's or PhD degree in Computer Science, Physics, Robotics, Computer Graphics, or a related field
• 3+ years of relevant experience in at least one of the core areas: scene simulation/compositing, synthetic data generation, 3D vision, or 3D augmentation
• Strong programming skills in Python or modern C++
• Hands-on experience with deep learning frameworks (PyTorch, TensorFlow) and generative models (diffusion models, NeRFs, Gaussian splatting, transformer-based world models)
• Solid background in computer graphics, 3D geometry, and simulation: rendering pipelines, physical simulation, procedural generation
• Experience with simulation environments such as Isaac Sim, Gazebo, Unreal, or Unity
• Excellent problem-solving skills
• Ability to work both independently and as part of a team
• Very good written and spoken English

Nice to have

• experience with CUDA is a plus
• Experience with synthetic data generation is advantageous
• Experience with sim-to-real transfer and deployment on robotics hardware (e.g. NVIDIA Jetson) is a plus

About the company

neura-robotics-gmbh