Senior Research Scientist - Video Generation Post-Training

SAIL TECHNOLOGY PRIVATE LIMITED; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

SAIL TECHNOLOGY PRIVATE LIMITED in Singapore seeks a senior researcher to design and implement video generation and post-training approaches that boost visual fidelity, temporal consistency, and controllability. The role focuses on diffusion-based models, evaluation pipelines, and alignment techniques, with cross‑functional collaboration to translate research into scalable product features.

Applicants should hold a Master’s degree or higher and have at least two years of research experience with

Qualifications

• 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 in video generation/restoration.
• First-author publication(s) at top-tier conferences (CVPR/ICCV/ECCV/ICLR/NeurIPS) on video generation, enhancement, or generative models.
• Experience developing diffusion-based generative models for visual content generation or enhancement with focus on fidelity and temporal quality.
• Experience with model post-training or fine-tuning, and familiarity with parameter-efficient fine-tuning or model distillation.
• Experience designing video quality evaluation methods or pipelines, including perceptual quality and temporal consistency.
• Strong programming and experimental skills; ability to work independently and with researchers, engineers, and product teams.

Responsibilities

• Design and implement video generation and post-training approaches to improve visual quality and instruction following.
• Explore video enhancement, super-resolution, restoration, and editing while preserving temporal consistency.
• Develop data and preference datasets; explore RLHF, DPO, GRPO, and PPO for alignment of generated videos.
• Build evaluation pipelines for visual fidelity, temporal consistency, motion quality, and adherence to prompts.
• Advance long-video generation, storyline and scene consistency, and controllable camera motion.
• Research diffusion-based models and acceleration techniques to improve inference speed and efficiency.
• Collaborate with researchers, engineers, and product teams to translate research ideas into scalable solutions.

Skills

Video generation

Video restoration

Diffusion models

RLHF alignment

PPO/GRPO/DPO

Experiment design

Collaboration

Education

Master's degree or above in CS/AI/CV

Job description

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.