Generative AI Researcher (3D, Video, and Agentic Intelligence)
Tencent Open · verified Sep 23, 2026 At a glance
Mid-level Video Production role at Tencent. Singapore-CapitaSky · full-time.
Pay not stated Video Production salary
Growth Roles summary, based on the employer's posting.
What you'll do
- Build AI systems for 3D assets, scenes, video, human motion, VLMs, and agentic reinforcement learning
- Run original research across computer vision, graphics, and embodied intelligence for virtual world creation
- Work with developers, artists, and designers to bring generated content into game experiences
- Track new methods in 3D generation, video understanding, multimodal reasoning, and simulation-based reinforcement learning
What you bring
- A PhD in computer vision, computer graphics, machine learning, robotics, or a related discipline
- Research depth in 3D or video generation, motion, VLMs, reinforcement learning, or agentic AI
- Publications in leading venues such as CVPR, SIGGRAPH, NeurIPS, ICML, or ICLR
- Deep learning experience with PyTorch or TensorFlow, including large-scale model training or evaluation
- Strong collaboration and communication skills for a fast-moving research setting
Who this fits
You'll fit a research-focused role developing AI for next-generation games, especially if your work covers one of the listed generation, vision, motion, or agentic intelligence areas. The position is full-time and based in Singapore at CapitaSky. You’ll collaborate with game developers, artists, and designers in a research-driven environment.
From the employer
Business Unit
LIGHTSPEED STUDIOS is made up of passionate players who advance the art & science of game development through great stories, great gameplay, and advanced technology. We are focused on bringing next generation experiences to gamers who want to enjoy them anywhere, anytime, across multiple genres and devices.About the Hiring Team
Lightspeed Tech Center is a R&D department under Lightspeed Studios which develop PUBG Mobile and other high-quality games. Our Tech Center leads the research, exploration, and discovery of innovative technologies and provides technical services for all games during all phases of life cycle, including engine, audio, QA, AI, next generation game, technical cooperation, etc.What the Role Entails
● Develop cutting-edge AI systems for 3D object and scene generation, video generation (world modeling), human motion capture and generation, multimodal vision-language models (VLM), and agentic reinforcement learning systems, tailored for next-generation game development.
● Conduct original research in computer vision, computer graphics, and embodied intelligence, driving innovation in generative AI pipelines for virtual world creation.
● Collaborate with cross-disciplinary teams — including game developers, artists, and designers — to integrate AI-generated content seamlessly into gameplay experiences.
● Continuously explore and apply the latest research trends in 3D generation, video understanding, multimodal reasoning, and simulation-based RL to enhance production efficiency and creativity in games.
Who We Look For
● PhD degree in Computer Vision, Computer Graphics, Machine Learning, Robotics, or a related field.
● Strong research background in at least one of the following areas:
– 3D Object or Scene Generation
– Video Generation / World Modeling
– Human Motion Capture or Generation
– Vision-Language Models (VLM)
– Reinforcement Learning / Agentic AI
● Publications in top-tier conferences or journals (CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, NeurIPS, ICML, ICLR, PAMI, IJCV, TOG, TVCG, etc.).
● Proficiency in deep learning frameworks (e.g., PyTorch, TensorFlow) and experience in large-scale model training or evaluation.
● Excellent teamwork and communication skills, with demonstrated ability to collaborate in a fast-paced, research-driven environment.
Preferred Qualifications:
● Hands-on experience with 3D modeling or rendering tools (Blender, Unreal Engine, Unity, etc.).
● Strong coding and prototyping ability in Python, C++, or similar languages.
● Familiarity with datasets and benchmarks related to 3D, motion, or video generation.
● Proven ability to translate research results into real-world interactive applications.
● Creativity and a passion for developing the next generation of AI-driven content creation tools
Equal Employment Opportunity at Tencent
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.
Not this one either?
Claude or ChatGPT reads the other 90,537 for you.
Get better matches →
