Generative AI - 3D Foundation Model

The role

You will drive the development of core 3D-native generative foundational models. This involves designing, training, and refining large-scale models and bridging the gap between research and product deployment.

What you will do

• Design, train, and refine large-scale 3D generative models.
• Bridge the gap between cutting-edge research and product.
• Deploy models in real products using human feedback and creative evaluation.
• Create novel model architectures for faster, higher-quality, and more controllable 3D generation.
• Collaborate with infrastructure and systems teams to build scalable training and data pipelines.
• Bring engineering discipline into a fast-paced research environment.
• Share insights and breakthroughs through internal demos, open-source contributions, or technical reports.

Required qualifications

• Strong engineering skills in Python and deep learning frameworks.
• 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.
• Communicate information and ideas so others will understand.
• Observe details at close range.
• Work under deadlines.

Nice to have

• PyTorch
• Familiar 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 / ML conferences

About the company

Meshy is a market leader in 3D generative AI that builds a full pipeline for 3D content. Their mission is to unleash creativity by making 3D creation boundless and accessible.