Machine Learning Engineer – 3D Mesh Reconstruction

Lit8 develops advanced AI systems for photorealistic visual content generation. In this role, you will develop methods for reconstructing high-quality, dense 3D meshes from images, focusing on geometric accuracy, fine surface detail, and photorealistic results.

We are looking for someone with strong hands-on experience in 3D reconstruction, surface geometry optimization, and computer graphics, capable of producing detailed, accurate, and editable 3D assets.

Minimum Qualifications

• Master’s degree or Ph.D. in Computer Science, Computer Graphics, Computer Vision, Machine Learning, or a closely related field.
• At least 2 years of hands‑on research or engineering experience in 3D reconstruction, including mesh reconstruction from images.
• Strong understanding of multi‑view geometry, camera models, and 3D reconstruction techniques.
• Experience reconstructing detailed 3D geometry, including surface normals, topology, and geometric consistency.
• Hands‑on experience with mesh optimization, surface reconstruction, or neural 3D representations.
• Strong programming skills in Python and experience with PyTorch or similar frameworks.
• Strong mathematical background in computer graphics, optimization, and 3D geometry.

Preferred Qualifications

• Ph.D. or research experience in computer graphics, 3D reconstruction, or related fields.
• Experience with differentiable rendering and inverse rendering.
• Knowledge of physically based rendering (PBR), ray tracing, and path tracing.
• Experience with Mitsuba 2/3, Dr.Jit, nvdiffrast, or similar rendering frameworks.
• Experience with neural signed distance fields (SDFs), implicit surfaces, or differentiable mesh optimization.
• Publications at SIGGRAPH, CVPR, ICCV, ECCV, or contributions to relevant open‑source projects.

Key Responsibilities

• Develop and optimize 3D mesh reconstruction methods for dense, high‑fidelity geometry from images.
• Improve mesh quality, topology, geometric accuracy, and surface detail.
• Explore physically based rendering (PBR) and inverse rendering techniques to improve materials, lighting, and photorealism.
• Evaluate reconstruction quality, geometric consistency, and visual fidelity.
• Collaborate with research and engineering teams to integrate reconstruction methods into production applications.

What We Offer

• The opportunity to work on advanced 3D reconstruction research with real product impact.
• A research‑driven environment focused on technical excellence and ownership.

If you are passionate about 3D reconstruction, computer graphics, and creating highly detailed, photorealistic 3D meshes, we'd love to hear from you.