Generative AI - 3D Foundation Model

Who You Are

You are a talented, hands-on researcher who thrives in a fast-paced environment, is self-directed, a team player, and knows how to get things done efficiently. You have deep understanding of the transformer architecture
, have strong python and tensor programming skills
, have a vision for AI beyond linear sequences, and you believe in "the scaling law". You can translate high-level goals into concrete research and implementation steps, set an approach, and follow through. When it's time to explain your ideas, you bring clarity to complex technical issues.
You are not afraid of confronting new ideas, and you are eager to share your knowledge with the team
. You use these skills to create real-world benefits for our researchers, engineers, and millions of users, and you are excited to help advance our effort to push the state of the art of AI that understands and generates 3D worlds.

At Meshy, we believe 3D creation should be boundless and accessible. Our mission statement is simple:
unleash creativity
. We built a full pipeline for 3D content ranging from text / image to 3D, texturing, texture editing, animation rigging, etc. We also built a vibrant community for our creators, where people can share their work, take inspiration from others, and even use it as an asset marketplace for their games and prototypes. We are the market leader in 3D generative AI, recognized as the No.1 in popularity among 3D AI tools (according to 2024 A16Z Games survey), and we generate real value and is used by enterprises (including Meta, Square Enix, Deepmind, etc.)

and millions of end users. Meshy is used in game and film production, in 3D printing, in industrial product design, in enablement of novel product features such as user-generated content, and even in training and simulation for robotics and physical AI.

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. In this role, you will join our foundational research to advance 3D AI, apply learnings from other fields of ML, and pushing the state of the art. You will also work towards long-term ambitious research goals, while identifying intermediate milestones.

The essential functions include, but are not limited to the following:

• 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 an 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.

• 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, and have an intuitive understanding of how models perceive, represent, and generate 3D worlds.
• Familiar with high performance training on large scale infrastructure (e.g., SLURM, Ray, k8s) is a plus.
• Contributions to popular open-source machine learning projects or publications in top-tier CV / ML conferences is a plus.

Trusted by Meta, Square Enix, Deepmind and more, Meshy is redefining 3D creation with generative AI. We empower artists, designers, engineers, hobbyists, and makers to bring immersive worlds, characters, and experiences to reality in minutes instead of months.

In…