Video Generation Research Intern - Controllable AI

Wwshemi; Mountain View (CA); On-site; USD 69,000 - 110,000; Full time

Job summary

HoYoverse is seeking a Research Scientist Intern in Video Generation in Mountain View, CA. You will work closely with research and engineering teams to advance post-training techniques for large-scale video generation models.

The focus is on controllability, generation quality, and temporal consistency, with opportunities to publish research and contribute to next-generation AI-powered content creation. Candidates should be pursuing a Master’s or PhD in CS/AI/ML, have strong Python and PyTorch

Qualifications

• Master's or PhD in CS/AI/ML or related field.
• Strong research background in video generation.
• Experience training or fine-tuning video generative models.

Responsibilities

• Research, develop, and implement post-training methods for video generation models, including supervised fine-tuning, preference optimization, and reinforcement learning-based approaches.
• Explore controllable video generation techniques to improve motion control, camera movement, trajectory following, and action-conditioned generation.
• Design and conduct experiments to improve video generation quality, temporal consistency, motion realism, and alignment with user instructions.
• Collaborate with researchers and engineers to develop training pipelines, evaluation benchmarks, and scalable experimentation workflows.
• Stay up to date with the latest advances in video generation and generative AI, and contribute to research publications and practical applications.

Skills

Python

PyTorch

Video generation

Research

Experimentation

Education

Master's or PhD in CS/AI/ML

Tools

Diffusion models

DiTs

Autoregressive models

Job description

HoYoverse is seeking a Research Scientist Intern in Video Generation in Mountain View, CA. You will work closely with research and engineering teams to advance post-training techniques for large-scale video generation models.

The focus is on controllability, generation quality, and temporal consistency, with opportunities to publish research and contribute to next-generation AI-powered content creation. Candidates should be pursuing a Master’s or PhD in CS/AI/ML, have strong Python and PyTorch