Research Scientist Intern (TikTok-Privacy Innovation Lab-Multimodal Generative Model) - 2026 Start (PhD)

Join TikTok's Privacy Innovation Lab as a Research Scientist Intern and contribute to the development of next-generation generative foundation models. The role involves working on large-scale model training systems, GPU-first architecture, and privacy-sensitive environments. You will participate in architecture design, optimization, and implementation of text-to-image and text-to-video models, focusing on DiT + Flow Matching / Rectified Flow-based generative models, and collaboration with systems and kernel engineers to map model designs to efficient implementations.

Requirements

• Currently pursuing PhD in Computer science, computer engineering, or a related technical discipline.
• Deep understanding of Diffusion / Flow Matching / Rectified Flow
• Strong familiarity with DiT / Transformer-based architectures in generative modeling
• Ability to debug the full pipeline from mathematical formulation → code → training → generated outputs
• Proficiency with PyTorch and hands-on experience training large-scale models