Business Unit

Technology Engineering Group (TEG) is responsible for supporting the company and its business groups on technology and operational platforms, as well as the construction and operation of R&D management and data centers. TEG provides users with a full range of customer services. As the operator of the largest networking, devices, and data center in Asia, TEG also leads the Tencent Technology Committee in strengthening infrastructure R&D through internal and distributed open source collaboration, constructing new platforms and supporting business innovation.

What The Role Entails

We are looking for research interns to work on next-generation 3D generation technologies and paradigms. The role is based in Singapore and will involve research and development across areas such as 3D vision, geometry processing, multimodal generation, and related topics.

Responsibilities

• Research high-fidelity geometric 3D representations that align with professional artists’ aesthetic standards and production requirements.
• Explore generative models built upon novel 3D representations, with a focus on generation quality, geometric accuracy, controllability, and scalability.
• Collaborate with researchers and engineers to translate research ideas into practical systems and real-world applications.

Who We Look For

• Strong programming and engineering skills.
• Solid understanding of machine learning, deep learning, and generative models.
• Research or project experience in at least one of the following areas:
  • 3D vision
  • Geometry processing
  • Multimodal generation
  • 3D generation
• Strong experimental design, data analysis, and problem-solving skills.
• Ability to independently implement, debug, and evaluate research ideas.
• Interest in developing next-generation 3D content generation technologies and applications.
• Candidates with experience across multiple relevant areas will be especially welcome.

Preferred Qualifications

• Experience with large-scale model training, distributed systems, or high-performance computing.
• Experience with 3D representations and methods such as meshes, point clouds, neural fields, Gaussian splatting, or differentiable rendering.
• Experience with multimodal foundation models, diffusion models, autoregressive models, or related generative architectures.
• Publications at top-tier conferences or journals in computer vision, machine learning, computer graphics, or related fields are a plus.
• Strong open-source projects or substantial research and engineering contributions in related areas are a plus.

What We Offer

• Sufficient computing resources to support large-scale experiments and fast research iteration.
• Access to industry-leading data assets for 3D and multimodal research.
• Opportunities to build upon the team’s research experience with state-of-the-art proprietary models.
• Exposure to the full research and development lifecycle, from early-stage exploration to large-scale model development and real-world deployment.
• Opportunities to collaborate with experienced researchers and engineers on next-generation 3D generation technologies.