Senior Video Generation R&D Scientist (World Models)

OriGen Tech Pte. Ltd.; Singapore; Presencial; SGD 150 000 - 210 000; Tempo integral

Resumo da oferta

Tencent in Singapore is seeking a research-focused engineer to develop world models for video and image generation. You will design datasets, build foundational architectures, and optimize training pipelines to accelerate R&D and deliver cutting-edge capabilities.

Strong candidates will have publications and hands-on experience with diffusion and autoregressive models, plus a track record in training/inference optimization and distributed systems for large models.

Qualificações

• 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.

Responsabilidades

• 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.
• 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.
• Explore alternative paradigms for implementing world models, investigate next-generation model architectures, and push the boundaries of what world models can achieve.

Conhecimentos

Deep learning fundamentals

Diffusion Models

Autoregressive Models

Training optimization

Formação académica

Bachelor's degree or higher in CS/AI/Math

Ferramentas

Text-to-image generation

Video generation

Descrição da oferta de emprego

Tencent in Singapore is seeking a research-focused engineer to develop world models for video and image generation. You will design datasets, build foundational architectures, and optimize training pipelines to accelerate R&D and deliver cutting-edge capabilities.

Strong candidates will have publications and hands-on experience with diffusion and autoregressive models, plus a track record in training/inference optimization and distributed systems for large models.