- 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 the "action input → video output" pipeline.
- Research hybrid architectures to achieve low-latency feedback for real-time interactive generation.
- Collaborate with Agent/RL teams to drive an end-to-end closed loop of "generation → understanding → control → feedback."
- Validate controllable interactive capabilities in game scenarios and lead the establishment of evaluation systems.
- Continuously track industry-related work and formulate proprietary technical roadmaps.
- Ph.D. in AI-related fields, covering areas such as video understanding, video prediction, reinforcement learning, or multimodal generation and understanding.
- Deep understanding of the internal mechanisms of both video generation and VLM models; familiar with diffusion model principles.
- Research experience in interactive video generation or controllable video generation.
- Ability to independently design complex model training pipelines with strong engineering skills.
- Proficient in Python/PyTorch, with publications in video understanding, controllable generation, or reinforcement learning.
- Experience with Game AI, simulation environments, or closed-loop systems is preferred.
- Relevant publications in top-tier conferences or journals are preferred.
As an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.
Skills Required
- Ph.D. in AI-related fields (video understanding, video prediction, reinforcement learning, multimodal generation/understanding)
- Deep understanding of internal mechanisms of video generation and Vision-Language Models (VLMs); familiarity with diffusion model principles
- Research experience in interactive or controllable video generation
- Ability to independently design complex model training pipelines and strong engineering skills
- Proficient in Python and PyTorch
- Publications in video understanding, controllable generation, or reinforcement learning (relevant top-tier publications preferred)
- Experience with Game AI, simulation environments, or closed-loop systems
Tencent Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Tencent and has not been reviewed or approved by Tencent.
-
Healthcare Strength — Healthcare coverage is positioned as a standout, with strong PPO options and relatively low prescription costs highlighted for U.S. plans. This suggests the medical offering can be a meaningful component of the overall rewards package for U.S.-based employees.
-
Retirement Support — Retirement support is framed as competitive in the U.S., with employer match details called out as an item to confirm in writing. This indicates retirement benefits can be a notable strength where applicable.
-
Strong & Reliable Incentives — Performance-linked incentives and share-based awards are repeatedly included as part of the compensation model, alongside potential RSU and sign-on eligibility in certain roles. This points to total rewards often extending beyond base pay through variable and equity components.
Tencent Insights
What We Do
Tencent uses technology to enrich the lives of Internet users. Our communications and social platforms Weixin and QQ connect users with each other, with digital content and daily life services in just a few clicks. Our high performance advertising platform helps brands and marketers reach out to hundreds of millions of consumers in China. Our financial technology and business services support our partners' business growth and assist their digital upgrade. We invest heavily in talent and technological innovation, actively participating in the development of the Internet industry. Tencent was founded in Shenzhen, China, in 1998, and listed on the Main Board of the Stock Exchange of Hong Kong since June 2004.
.jpeg)
