Senior Researcher-Video Generation

Tencent; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Tencent Technology Engineering Group seeks researchers to advance large-scale world models. You will design training datasets, craft model architectures, and optimize pre-training and downstream pipelines, ensuring leadership in capabilities and performance.

This role requires a strong foundation in deep learning, experience with diffusion and autoregressive models, and a track record in large-model R&D. Collaboration and curiosity are essential in a fast-evolving environment.

Qualifications

• Bachelor’s degree or higher in CS, AI, Mathematics or related field (full-time education).
• Solid foundation in deep learning; hands-on experience in large-model R&D; Diffusion & Autoregressive models preferred; publications a plus; experience in text-to-image/video generation helps.

Responsibilities

• Engage in R&D of large-scale world models: dataset design, model architecture, training pipelines, and evaluation.
• Identify bottlenecks, derive solutions from first principles, accelerate development and iteration of world models.
• Explore next-gen architectures and alternative paradigms to push the capabilities of world models.

Skills

Deep learning

Diffusion models

Autoregressive models

Distributed training

Text-to-image generation

Education

Bachelor’s degree or higher in Computer Science / AI / Mathematics

Tools

Distributed training frameworks

Job description

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

• 1. Engage in the R&D of large-scale video world models, including the design and construction of training datasets, foundational model architecture design, optimization of pre-training/SFT/RL pipelines, model capability evaluation, and exploration of diverse downstream application scenarios.
• 2. Conduct scientific analysis of R&D challenges, identify performance bottlenecks, and derive solutions from first principles to accelerate the development and iteration of world models, ensuring competitive edge and technical leadership.
• 3. Explore alternative paradigms for implementing world models, investigate next-generation model architectures, and push the boundaries of what world models can achieve.

Who We Look For

• 1. Bachelor's degree or higher (preferred) in Computer Science, Artificial Intelligence, Mathematics, or related fields (full-time education required).
• 2. Solid foundation in deep learning algorithms and proven hands-on experience in large model R&D. Experience with Diffusion Models and Autoregressive Models is highly preferred. Publications in top-tier conferences/journals and practical experience in text-to-image/video generation are strong pluses.
• 3. Proficient in the underlying implementation details of various deep learning networks and operators; experienced in training/inference optimization, CPU/GPU acceleration, and distributed training/inference acceleration. Practical experience is highly valued.
• 4. Exceptional candidates with ACM-ICPC or NOIP competition experience will be given top priority.
• 5. Strong learning agility, effective communication skills, teamwork spirit, and a keen sense of curiosity.

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.