Generative AI - 3D Foundation Model

Responsibilities

• Design, train, and refine large-scale 3D generative models covering pre-training, post-training, and emerging paradigms in diffusion, flow matching, and multi-modal learning
• Bridge the gap between cutting-edge research and product by deploying models used by millions of creators
• Create novel model architectures to improve 3D generation speed, quality, and controllability
• Collaborate with infrastructure and systems teams to build scalable training and data pipelines across GPU clusters
• Bring engineering discipline to research through elegant code and reproducible experiments
• Share insights through internal demos, open-source contributions, or technical reports

Requirements

• Strong engineering skills in Python and deep learning frameworks (preferably PyTorch)
• Familiarity with Transformers and modern generative AI models such as Diffusion, flow matching, and VAE
• Deep understanding of transformer architecture and tensor programming
• Ability to move between research prototypes and production systems

Preferred Qualifications

• Experience with high-performance training on large-scale infrastructure (e.g., SLURM, Ray, k8s)
• Contributions to popular open-source machine learning projects
• Publications in top-tier CV or ML conferences

About the Company

Meshy is a market leader in 3D generative AI, providing a full pipeline for 3D content creation ranging from text/image to 3D, texturing, and animation. Trusted by enterprises like Meta, Square Enix, and Deepmind, Meshy aims to unleash creativity by making 3D creation boundless and accessible.