Video Generation & Understanding Researcher

L&Q OASIS PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Tencent Lightspeed Studios is seeking a research-focused expert in AI to advance video understanding and controllable generation for next-gen games. You will work in the Lightspeed Tech Center, collaborating with RL and agent teams to build end-to-end pipelines from generation to feedback. Strong publications and PyTorch experience are highly valued.

The role requires a Ph.D. in AI-related fields and a deep understanding of diffusion models, video generation, and multimodal understanding.

Qualifications

• Ph.D. in AI-related fields covering video understanding, video prediction, RL or multimodal generation.
• Deep understanding of video generation and VLM diffusion models.
• Experience with interactive video generation or controllable generation.
• Proficient in Python/PyTorch with relevant publications.
• Experience with game AI or simulation environments is preferred.

Responsibilities

• Research the model's ability to understand generated content, parsing semantics, objects, relationships, and spatial structures.
• Implement state tracking and consistency modeling for generated videos.
• Explore unified generation-understanding model architectures.
• Research causal consistency control and physical constraints for action input → video output.
• Research hybrid architectures to achieve low-latency feedback for real-time generation.
• Collaborate with Agent/RL teams to drive a closed loop of generation → understanding → control → feedback.
• Validate controllable interactive capabilities in game scenarios and establish evaluation systems.
• Continuously track industry work and formulate proprietary technical roadmaps.

Skills

Ph.D. in AI

Video understanding

Video generation

Reinforcement learning

Multimodal understanding

Python

PyTorch

Publications in AI

Education

Ph.D. in AI-related fields

Tools

Diffusion models

Game AI frameworks

Simulation environments

Job description

Tencent Lightspeed Studios is seeking a research-focused expert in AI to advance video understanding and controllable generation for next-gen games. You will work in the Lightspeed Tech Center, collaborating with RL and agent teams to build end-to-end pipelines from generation to feedback. Strong publications and PyTorch experience are highly valued.

The role requires a Ph.D. in AI-related fields and a deep understanding of diffusion models, video generation, and multimodal understanding.