Senior Research Scientist Video Generation Post-Training

sail technology private limited; Singapore; Presencial; SGD 120 000 - 180 000; Tempo integral

Resumo da oferta

Sail Technology Private Limited is seeking a research-focused professional in Singapore to advance video generation, enhancement, and alignment. The role emphasizes post-training methods, diffusion-based models, and collaborations across research and engineering teams.

The ideal candidate holds a Master’s in CS/AI/CV with 2+ years of hands-on experience, including first-author papers, and a strong foundation in diffusion models, RLHF, and evaluation pipelines.

Qualificações

• Master’s degree or higher in CS/AI/CV or related field.
• ≥2 years of full-time research in CV and generative AI with video experience.
• First-author papers at CVPR/ICCV/ECCV/ICLR/NeurIPS on video topics.
• Experience with diffusion-based generative models for visual content.
• Familiar with post-training, fine-tuning, and parameter-efficient methods.
• Experience designing video quality evaluation pipelines.
• Strong programming and experimental skills; able to work independently and in teams.

Responsabilidades

• Design and develop post-training approaches for video generation models.
• Explore video enhancement, super-resolution, restoration, editing.
• Develop datasets for instruction and preference alignment; RLHF, DPO, GRPO, PPO.
• Build evaluation pipelines for fidelity, temporal consistency, and video quality.
• Advance controllable long-video generation and camera motion control.
• Investigate model distillation and acceleration for diffusion-based models.
• Collaborate with researchers, engineers, and product teams.

Conhecimentos

Video generation

Generative AI

Computer vision

Diffusion models

Research experimentation

Publication track record

Python programming

Formação académica

Master's degree in CS/AI/CV

Ferramentas

PyTorch

TensorFlow

RLHF

Model distillation

Experiment tracking

Descrição da oferta de emprego

Job Description:

• Video Generation and Post-Training: Design and develop post-training approaches for video generation models to improve visual quality, instruction following, motion realism, and overall generation fidelity.
• Video Enhancement and Restoration: Explore generative approaches to video super-resolution, restoration, and editing, enhancing detail and perceptual quality while preserving temporal consistency.
• Data and Preference Alignment: Develop high-quality instruction and preference datasets for video post-training. Explore alignment techniques such as RLHF, DPO, GRPO, and PPO to improve generated videos according to human preferences.
• Video Quality Evaluation: Build evaluation pipelines covering visual fidelity, temporal consistency, motion quality, prompt adherence, and human preference. Research video quality assessment methods and multi-dimensional reward models to support model optimization.
• Controllable and Consistent Generation: Advance capabilities in long-video generation, storyline consistency, object and scene consistency, and precise control over camera movement and motion.
• Efficient Inference: Research and implement model distillation and other acceleration techniques for diffusion-based video models, improving inference speed and reducing computational and memory requirements.
• Research and Collaboration: Stay current with advances in video generation and multimodal AI, translate research ideas into scalable solutions, and collaborate with researchers, engineers, and product teams.

Requirements:

• Master’s degree or above in Computer Science, Artificial Intelligence, Computer Vision, or a related field.
• Minimum 2 years of full-time research experience in computer vision and generative AI, with hands-on experience in video generation, video restoration, video super-resolution, or video editing.
• First-author publication(s) at top-tier conferences (CVPR/ICCV/ECCV/ICLR/NeurIPS) on video generation, video enhancement, or generative models.
• Demonstrated experience developing diffusion-based generative models for visual content generation or enhancement, with a strong understanding of visual fidelity, temporal consistency, and perceptual quality.
• Experience with model post-training or fine-tuning, and familiarity with approaches such as parameter-efficient fine-tuning, preference alignment, or model distillation.
• Experience designing video quality evaluation methods or pipelines, including the assessment of perceptual quality and temporal consistency.
• Strong programming and experimental skills, with the ability to investigate research problems, design experiments, and translate research ideas into effective solutions.
• Good problem analysis and research skills; sustained curiosity about advances in video generation and multimodal AI; and the ability to work independently and collaboratively across research and engineering teams.