Controllable Video Generation Researcher
Core
Design multimodal controllable video generation frameworks for game inputs (keyboard, controller, trajectory, voice) to enable low-latency, collaborative player control.
Role type
Senior IC research scientist (controllable video generation)
Builds
Controllable video generation capabilities for multi-player collaborative control and game engine integration
Domain
Gaming + Generative AI (Diffusion models, Reinforcement Learning)
Deliverable
production ML models
Required skills
Conditional generation models, Diffusion models, Trajectory/Camera/Motion/Posture control, Game engine input/output logic, Python, PyTorch
Preferred skills
Game AI, Real-time/interactive video generation, Reinforcement Learning post-training
Technologies
PyTorch, Diffusion models, Reinforcement Learning
Responsibilities
Design multimodal generation frameworks, Research high-fidelity generation under sparse control, Decouple and combine control modules, Develop multi-player collaborative control capabilities, Collaborate on standardized interfaces, Drive joint optimization with RL
Seniority
Senior, hands-on IC
