Generative AI - 3D Foundation Model

As a core member of the team of research scientists and machine learning engineers at Meshy, you will drive the development of our core 3D-native generative foundational model.

Responsibilities

Design, train, and refine large-scale 3D generative models from 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, deploy models in real products used by millions of creators, using human feedback and creative evaluation; Create novel model architectures to make 3D generation faster, higher-quality, and more controllable; Collaborate with infrastructure and systems teams to build scalable training, and data pipelines across GPU clusters and cloud environments; Bring engineering discipline into a fast-paced research environment: elegant code, reproducible experiments, and building software as a team; Share insights and breakthroughs through internal demos, open-source contributions, or technical reports that advance the field of 3D generative AI

Requirements

Deep understanding of the transformer architecture; Strong Python and tensor programming skills; Vision for AI beyond linear sequences; Belief in 'the scaling law'; Ability to translate high-level goals into concrete research and implementation steps; Ability to set an approach and follow through; Ability to bring clarity to complex technical issues; Not afraid of confronting new ideas; Eager to share knowledge with the team; Strong engineering skills in Python and deep learning frameworks (preferably PyTorch); Comfortable moving between research prototypes and production systems; Familiar with Transformers and modern generative AI models (Diffusion / flow matching, VAE, etc.); Curiosity and passion for multi-modal AI; Intuitive understanding of how models perceive, represent, and generate 3D worlds

Nice to have

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