Research Engineer - Graphics

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.

We are looking for a research engineer with a deep graphics understanding to bridge the gap between high-end rendering and frontier AI. You will lead the creation of the synthetic engines that power our models, designing scalable pipelines that generate the ground-truth reality for our next-generation world models. If you are a graphics expert who wants to move beyond visual effects and start building the training grounds for world Intelligence, we want you on our team.

Responsibilities

- Design and architect high-fidelity synthetic data engines to train large-scale World Models.

- Develop and scale automated rendering pipelines to generate diverse, physically-consistent 3D environments.

- Integrate and refine rendering workflows using tools like Blender, Unity, 3DMax, or equivalent platforms.

- Work with our world-class research team to ensure datasets and synthetic data workflows align with our world model training objectives.

Key Qualifications

- Strong background in computer graphics with a proven track record of building complex rendering systems or high-fidelity simulation environments.

- Deep understanding of 3D representations (meshes, voxels, point clouds, implicit surfaces, etc.); knowledge in 3D Gaussian Splatting and volumetric rendering is a nice to have.

- Proficiency in Blender, Unity, Unreal Engine, 3DMax, or similar rendering and simulation software.

- Bachelor’s, Master’s, or equivalent experience in computer science, graphics, or related fields.

- Nice to have: experience, or ambition to work with procedural generation tools and techniques.

- Background in large-scale data workflows for AI/ML model training.