<p><strong>Research Scientist – Controlled 3D Generation</strong></p>
<p><strong>Location:</strong> Remote</p>
<p><strong>About the Role</strong></p>
<p>We’re seeking a Research Scientist passionate about <strong>3D...
...
<p><strong>Research Scientist – Controlled 3D Generation</strong></p>
<p><strong>Location:</strong> Remote</p>
<p><strong>About the Role</strong></p>
<p>We’re seeking a Research Scientist passionate about <strong>3D generation, flow matching, and diffusion models</strong>. You’ll help advance the frontier of controllable 3D content creation—building models that generate consistent, editable, and physically grounded 3D assets and scenes.</p>
<p><strong>What You’ll Do</strong></p>
<ul>
<li>Conduct cutting-edge research on <strong>flow-matching, diffusion, and score-based methods</strong> for 3D generation and reconstruction.</li>
<li>Design and implement scalable training pipelines for controllable 3D generation (meshes, Gaussians, NeRFs, voxels, implicit fields).</li>
<li>Develop techniques for <strong>conditioning and control</strong> (text, sketch, pose, camera, physics) and multi-view consistency.</li>
<li>Analyse model behaviour through ablations, visualisations, and quantitative metrics.</li>
<li>Collaborate with cross-disciplinary research, graphics, and infrastructure teams to translate research into production-ready systems.</li>
<li>Publish results at top-tier venues and work with interns.</li>
</ul>
<p><strong>What You Bring</strong></p>
<ul>
<li>PhD (or equivalent experience) in Machine Learning, Computer Vision, or Computer Graphics.</li>
<li>Published work on <strong>diffusion, flow-matching, or score-based generative models</strong> (2D or 3D).</li>
<li>Strong engineering and problem-solving abilities: experience with <strong>PyTorch, JAX, or CUDA-level optimisation</strong>.</li>
<li>Understanding of <strong>3D representations</strong> (meshes, Gaussians, signed-distance fields, volumetric grids, implicit networks).</li>
<li>Solid grasp of <strong>geometry processing, multi-view consistency, and differentiable rendering</strong>.</li>
<li>Ability to scale experiments efficiently and communicate complex results clearly.</li>
</ul>
<p><strong>Bonus / Preferred</strong></p>
<ul>
<li>Experience generating <strong>coherent 3D scenes</strong> with multiple interacting objects, lighting, and spatial layout.</li>
<li>Familiarity with <strong>scene-level control</strong> (object placement, camera path, simulation, or text-to-scene composition).</li>
<li>Knowledge of <strong>video-to-3D</strong>, <strong>image-to-scene</strong>, or <strong>4D temporal generation</strong>.</li>
<li>Background in <strong>physically-based rendering</strong>, <strong>simulation</strong>, or <strong>world-model architectures</strong>.</li>
<li>Track record of impactful publications or open-source releases.</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>