Research Scientist, Professional Creative Workflows

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Conduct original research in generative AI aimed at enhancing professional creative workflows across various mediums, including image, video, 3D, vector graphics, and design.

• Develop innovative methods that push the boundaries of current technology while ensuring practical relevance to real-world creative and production processes.

• Publish research findings in prominent academic venues when appropriate, while also contributing to impactful internal projects.

• Investigate multimodal generative systems that seamlessly integrate image, video, 3D, vector graphics, and design, focusing on aspects such as controllability, editability, and the creation of reusable assets.

• Transform research insights into prototypes, experiments, and model capabilities that can guide product development.

• Collaborate with researchers, engineers, designers, and product teams to pinpoint significant research challenges that will have meaningful downstream effects.

• Design datasets, benchmarks, and evaluation protocols tailored for professional workflows where quality, editability, consistency, brand compliance, and production utility are essential.

• Remain at the cutting edge of generative media research and identify opportunities to merge concepts from computer graphics, vision, language, video, and creative tools.

• Foster a research culture that prioritizes technical expertise, intellectual diversity, high publication standards, and practical significance.

⛳️ Requirements

• Proven academic research history in fields such as computer vision, computer graphics, machine learning, generative modeling, computational imaging, visual computing, or a related area.

• PhD or equivalent research experience in Computer Science, Machine Learning, Computer Graphics, Computer Vision, or a closely aligned discipline.

• Demonstrated capability to conduct original research, publish scholarly articles, and create functional systems or prototypes.

• Experience in generative and multimodal modeling, covering aspects like diffusion models, transformers, 3D generation, neural rendering, inverse rendering, video generation, image editing, controllable generation, or design automation.

• Broad technical expertise across several of the following domains:

• Generative image models

• Video generation or video editing

• 3D asset generation, reconstruction, neural rendering, or geometry processing

• Differentiable rendering, inverse rendering, materials, lighting, or relighting

• Vector graphics, layout, typography, or design systems

• Multimodal representation learning

• Experience in professional media, VFX, games, e-commerce, design, or creative tooling

• Proficient programming skills in Python and PyTorch, capable of implementing, adapting, and extending modern research code.

• Ability to evaluate both research and workflow quality, considering factors like controllability, iteration speed, editability, consistency, reliability, and integration into existing creative processes.

• Strong communication skills to clearly articulate research concepts to both research-focused and product-oriented collaborators.

• Demonstrated creative technical judgment: the aptitude for synthesizing ideas from diverse fields into new research trajectories rather than merely making incremental enhancements to existing systems.

🏝️ Benefits

• Equal Employment Opportunity