<p><strong>Research Scientist – Geometry (AI Assisted)</strong></p>
<p><strong>Location:</strong> Remote</p>
<p><strong>About the Role</strong></p>
<p>We’re looking for a Research Scientist with a strong foundation in <...
...
<p><strong>Research Scientist – Geometry (AI Assisted)</strong></p>
<p><strong>Location:</strong> Remote</p>
<p><strong>About the Role</strong></p>
<p>We’re looking for a Research Scientist with a strong foundation in <strong>geometry processing</strong> and a deep interest in how modern learning systems can represent and reconstruct shape. You’ll work at the intersection of <strong>discrete and differential geometry, shape tokenization, and generative modelling</strong>, developing methods for unwrapping, remeshing, and reconstructing 3D geometry that are compact, controllable, and scalable.</p>
<p><strong>What You’ll Do</strong></p>
<ul>
<li>Research and develop <strong>AI-assisted geometry processing</strong> pipelines for UV unwrapping, remeshing, geometric reconstruction, and shape generation.</li>
<li>Design <strong>learning-based representations</strong> for geometry (meshes, point clouds, implicit fields) that capture structure, topology, and correspondence.</li>
<li>Develop <strong>token- or patch-based encoders</strong> for shape representation, enabling compression, editing, and reconstruction from learned codes.</li>
<li>Integrate learned geometry modules into <strong>generation and reconstruction frameworks</strong>, ensuring geometric validity and multi-view consistency.</li>
<li>Build training and evaluation pipelines with quantitative metrics for distortion, reconstruction fidelity, and mesh topology quality.</li>
<li>Collaborate with graphics, simulation, and ML teams to bring new geometry models into creative and production pipelines.</li>
<li>Contribute to publications, benchmarks, and internal best practices in geometry + AI research.</li>
</ul>
<p><strong>What You Bring</strong></p>
<ul>
<li>PhD (or equivalent experience) in Computer Graphics, Geometry Processing, Machine Learning, or a related field.</li>
<li>Deep understanding of <strong>discrete and differential geometry</strong>, including remeshing, surface parameterization, and geometric optimization.</li>
<li>Experience with <strong>learning-based geometry representations</strong> (e.g., geometric autoencoders, tokenization, learned unwrapping, or generative reconstruction).</li>
<li>Strong engineering skills: proficiency with PyTorch/JAX, geometry/mesh libraries, and large-scale experiment pipelines.</li>
<li>Ability to bridge classical geometry processing with modern learning-based techniques and apply them to practical 3D workflows.</li>
</ul>
<p><strong>Bonus / Preferred</strong></p>
<ul>
<li>Research or open-source work in <strong>learning-based UV unwrapping, remeshing, or geometry reconstruction</strong>.</li>
<li>Experience developing <strong>generative 3D models</strong> or integrating learned geometry modules into diffusion / flow-matching frameworks.</li>
<li>Familiarity with <strong>implicit neural representations</strong>, <strong>differentiable rendering</strong>, or <strong>geometry-aware latent spaces</strong>.</li>
<li>Experience integrating geometry systems into 3D toolchains (e.g., Blender, Unreal, Unity) or graphics pipelines.</li>
</ul>
<p><strong>Equal Employment Opportunity:</strong></p>
<p>We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.</p>
