Video Generation Content Understanding and Feedback Researcher
Core
Research model capabilities to understand generated video content, including semantics, objects, relationships, and spatial structures, while implementing state tracking and consistency modeling.
Role type
Senior Research Scientist (Video Generation & Understanding)
Builds
Proprietary technical roadmaps and evaluation systems for controllable interactive video generation pipelines.
Domain
AI Research, Video Generation, Game AI
Deliverable
production ML models
Required skills
Video understanding, video prediction, reinforcement learning, multimodal generation and understanding, diffusion model principles, complex model training pipeline design, Python, PyTorch
Preferred skills
Interactive video generation, controllable video generation, Game AI, simulation environments, closed-loop systems, top-tier conference publications
Technologies
PyTorch, diffusion models, VLMs
Responsibilities
Research causal consistency control and physical constraints for action-to-video pipelines, explore unified generation-understanding architectures, collaborate with Agent/RL teams for end-to-end closed-loop systems, validate controllable interactive capabilities in game scenarios, track industry work and formulate technical roadmaps
Seniority
Senior, hands-on IC
