Senior Research Scientist/Software Engineer, TikTok-Neural Graphics and World Models

What you'll do

• Lead research directions across neural graphics, world models, 3D modeling, animation, simulation, or rendering.
• Develop and evaluate AI models, representations, data strategies, and evaluation methods for interactive graphics and world generation.
• Build research prototypes and collaborate with engineering teams to integrate successful models into real-time engine workflows.

What they ask for

• PhD/MS or equivalent research experience in machine learning, computer graphics, robotics, applied mathematics, or a related technical field.
• Relevant research or industry experience in neural graphics, generative AI, computer graphics, world models, or a closely related domain; doctoral research may count.
• Hands-on experience training or adapting generative models, plus strong modern machine-learning knowledge and engineering fluency with PyTorch or JAX.
• Deep expertise in at least one AI-for-graphics area, with demonstrated ability to formulate hypotheses, design controlled experiments, and collaborate on translating research prototypes into engine pipelines.

Nice to have

• Publications at leading research venues such as SIGGRAPH, CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, RSS, or CoRL.
• Experience with novel AI-for-graphics methods, multimodal 3D/world generation, interactive-world learning or control, or real-time engine workflows.

Tools

PyTorch, JAX, variational autoencoders, latent tokenizers, diffusion, flow-matching models, diffusion transformers, autoregressive models

AI focus

Develops and evaluates generative AI models, neural representations, data strategies, and evaluation methods for neural graphics, 3D content, world models, and interactive graphics systems.