Research Scientist, Professional Creative Workflows

Stability
Anywhere
Workplace: RemoteFull timeFunction: Data Science & Machine LearningEducation: phdSkills: ["Communication","Collaboration","Research quality reasoning","Creative technical judgment","Prototype building"]

Advance generative AI research for professional creative workflows across image, video, 3D, vector graphics, and design. Build multimodal methods focused on controllability, editability, and reusable asset creation, then translate research into prototypes that inform product direction. Partner with researchers, engineers, designers, and product teams to define high-impact research problems, datasets, benchmarks, and evaluation protocols for workflow quality, consistency, and production usefulness.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Stability
Stability
1 month ago

Research Scientist, Professional Creative Workflows

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live

Job Summary

Advance generative AI research for professional creative workflows across image, video, 3D, vector graphics, and design. Build multimodal methods focused on controllability, editability, and reusable asset creation, then translate research into prototypes that inform product direction. Partner with researchers, engineers, designers, and product teams to define high-impact research problems, datasets, benchmarks, and evaluation protocols for workflow quality, consistency, and production usefulness.
Location: Anywhere
Workplace: Remote
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Conduct original generative AI research for professional creative workflows across image, video, 3D, vector graphics, and design.
  • •Develop state-of-the-art methods relevant to real creative and production workflows.
  • •Explore multimodal generative systems emphasizing controllability, editability, and reusable asset creation.
  • •Translate research insights into prototypes, experiments, and model capabilities that can inform product direction.
  • •Design datasets, benchmarks, and evaluation protocols for workflow quality, editability, consistency, brand adherence, and production usefulness.

Key Requirements

  • •PhD (or equivalent research experience) in Computer Science, Machine Learning, Computer Graphics, Computer Vision, or a closely related discipline.
  • •Strong academic research track record in computer vision, computer graphics, machine learning, generative modeling, computational imaging, or visual computing.
  • •Demonstrated ability to conduct original research, publish papers, and build working systems or prototypes.
  • •Experience with generative and multimodal modeling, including diffusion models, transformers, 3D generation, neural rendering/inverse rendering, video generation, image editing, controllable generation, or design automation.
  • •Strong programming skills in Python and PyTorch, and the ability to reason about both research quality and workflow quality (controllability, editability, consistency, reliability, and integration).
Experience:Generative AIMultimodalComputer visionComputer graphicsCreative tooling
Education:PhD / Doctorate in Computer Science, Machine Learning, Computer Graphics, Computer Vision (or closely related discipline)
Skills:CommunicationCollaborationResearch quality reasoningCreative technical judgmentPrototype building
Languages:English
Tech Stack:PythonPyTorchTransformersDiffusion models

Company Brief

Stability
Develops open-source generative AI models and tools, including image synthesis (Stable Diffusion) and multimodal foundations, enabling creators and businesses to build AI-driven media and applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: London, United Kingdom
Founded: 2020
WebsiteLinkedIn