Generative AI Researcher (3D, Video, and Agentic Intelligence)
On-site · Singapore, Singapore
Job Summary
Develop cutting-edge AI systems for 3D object and scene generation, video generation, human motion capture and generation, and multimodal vision-language models. Conduct original research in computer vision, computer graphics, and embodied intelligence. Collaborate with cross-disciplinary teams to integrate AI-generated content into gameplay. Explore latest trends in 3D generation, video understanding, multimodal reasoning, and simulation-based RL.
Required Qualifications
- 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
Desired 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
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.