Research Scientist, Professional Creative Workflows

Stabilityai; United States; À distance; USD 120 000 - 180 000; Plein temps

Résumé du poste

StabilityAI is seeking a Research Scientist for professional creative workflows, spanning image, video, 3D, vector graphics, and design. The role blends frontier research with practical prototypes to impact products used by creators and enterprises.

You will explore multimodal systems, publish at top venues when appropriate, and translate insights into prototypes and model capabilities that steer product direction.

Qualifications

• Strong academic research track record in computer vision, graphics, machine learning, generative modeling, or related fields.
• PhD or equivalent research experience in Computer Science, ML, CV, or graphics.
• Demonstrated ability to publish papers and build working systems or prototypes.

Responsabilités

• Conduct original research in generative AI for professional creative workflows across image, video, 3D, vector graphics, and design.
• Develop methods that advance state of the art with real creative and production relevance.
• Publish research at leading venues while contributing to high-impact internal projects.

Connaissances

Strong research

Python

PyTorch

Multimodal modeling

Communication

Formation

PhD or equivalent

Outils

Python

PyTorch

Description du poste

Research Scientist, Professional Creative Workflows

About the Role

We are seeking a highly motivated Research Scientist to join our Research team. The role focuses on advancing the next generation of generative AI systems for professional creative workflows, spanning image, video, 3D, vector graphics, and design. This is a general research role with room for academic publication, long-horizon exploration, and technically ambitious work, while remaining grounded in real projects with meaningful product impact. The ideal candidate can move fluidly between frontier research, rigorous experimentation, and prototype systems that inform how professional creators work with generative AI. We are looking for a broad, technically deep researcher who can combine ideas across fields and modalities, connecting concepts from areas such as computer vision, graphics, generative modeling, and design to address complex creative workflows. You will work on research that enables creators and enterprises to generate, edit, structure, refine, and reuse visual assets across modalities, supporting workflows in which different forms of media and design intent work together rather than as isolated generation tasks.

Responsibilities

• Conduct original research in generative AI for professional creative workflows across image, video, 3D, vector graphics, and design.
• Develop new methods that advance the state of the art while remaining relevant to real creative and production workflows.
• Publish research at leading academic venues where appropriate, while also contributing to high-impact internal projects.
• Explore multimodal generative systems that integrate image, video, 3D, vector graphics, and design, with an emphasis on controllability, editability, and reusable asset creation.
• Translate research insights into prototypes, experiments, and model capabilities that can inform product direction.
• Work with researchers, engineers, designers, and product teams to identify important research problems with meaningful downstream impact.
• Design datasets, benchmarks, and evaluation protocols for professional workflows where quality, editability, consistency, brand adherence, and production usefulness matter.
• Stay at the frontier of generative media research and identify opportunities to combine ideas across computer graphics, vision, language, video, and creative tooling.
• Contribute to a research culture that values technical depth, intellectual breadth, publication quality, and practical relevance.

Qualifications

• Strong academic research track record in computer vision, computer graphics, machine learning, generative modeling, computational imaging, visual computing, or a related field.
• PhD or equivalent research experience in Computer Science, Machine Learning, Computer Graphics, Computer Vision, or a closely related discipline.
• Demonstrated ability to conduct original research, publish papers, and build working systems or prototypes.
• Experience in generative and multimodal modeling, including areas such as diffusion models, transformers, 3D generation, neural rendering, inverse rendering, video generation, image editing, controllable generation, or design automation.
• Broad technical background across several of the following areas: 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 Professional media, VFX, games, e-commerce, design, or creative tooling
• Strong programming skills in Python and PyTorch, with the ability to implement, adapt, and extend modern research code.
• Ability to reason about both research quality and workflow quality, including controllability, iteration speed, editability, consistency, reliability, and integration into existing creative processes.
• Strong communication skills, with the ability to explain research ideas clearly to both research and product-oriented collaborators.
• Evidence of creative technical judgment: the ability to combine ideas from different fields into new research directions rather than only incrementally improving existing systems.
• Highly Desirable Publications at top‑tier venues such as CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, NeurIPS, ICLR, ICML, or related venues.
• Research experience spanning more than one modality, especially across image, video, 3D, vector graphics, design, or multimodal generation.
• Experience with professional creative domains such as VFX, games, animation, product visualization, advertising, graphic design, or 3D asset production.
• Experience with controllable generation, layered image editing, material and lighting decomposition, multi‑view consistency, relightable assets, vector‑aware generation, or structured design outputs.
• Experience building research prototypes that influence product direction or enable new…