Research Scientist/Software Engineer

About the Role

Join the TikTok Engine & Tools AI-3D team, building a next-generation AI-native graphics engine for games and interactive experiences across TikTok and future creative platforms. This role focuses on cutting-edge 3D generation technologies, aiming to transform the 3D production pipeline into an AIGC-driven paradigm.

Key Responsibilities

• Pursue bold ideas and tackle complex challenges.
• Work on 3D asset and scene generation, character animation, physics simulation, neural rendering, and real-time interactive systems.
• Develop data pipelines, runtimes, and evaluation frameworks for persistent, controllable, and responsive digital worlds.
• Transform research into practical technologies for interactive content.
• Understand recent research, design controlled experiments, analyze failures, and contribute to model training, data, or evaluation workflows.
• Collaborate with Software Engineers to move research prototypes into interactive engine pipelines.

Requirements & Tech Stack

• Machine learning
• Generative modeling
• Experimental methodology
• Frameworks such as PyTorch or JAX
• Generative architectures and training methods including variational autoencoders, latent tokenizers, diffusion or flow-matching models, diffusion transformers, autoregressive models, multimodal transformers, long-context modeling, pre-training, or post-training.
• Model development workflows
• AI-for-graphics areas: 3D modeling, asset generation, 3D representations, animation, motion generation, simulation, physics-aware learning, rendering, neural rendering, world models, video prediction, graphics, and game-engine workflows.

Qualifications

• Completing or recently completed a PhD degree in computer science, computer engineering, electrical engineering, applied mathematics, or a related discipline.
• Research experience through a laboratory, thesis, publication, internship, open-source project, or substantial independent project.
• Strong, up-to-date foundation in machine learning, generative modeling, and experimental methodology.
• Hands-on experience building, training, fine-tuning, or evaluating models.
• Familiarity with modern generative architectures and training methods.
• Engineering fluency with model development workflows.
• Deep experience in at least one of the specified AI-for-graphics areas.
• Ability to understand recent research, design controlled experiments, analyze failures, and contribute to model training, data, or evaluation workflows.
• Interest in collaborating with Software Engineers.

Preferred Qualifications

• Peer-reviewed publications at leading venues such as SIGGRAPH, CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, RSS, CoRL, or related research communities.
• Strong technical reports, open-source contributions, demos, project pages, or research projects.
• Experience with 3D or world generation conditioned on text, images, video, actions, or structured scene inputs.