Staff Applied Scientist, 3D - Firefly Foundry

Adobe Systems
San Jose, Seattle, San Francisco
Workplace: OnsiteFull timeUSD 164,000 - 313,300 annuallyFunction: Research & Scientific (R&D)Experience: 8+ yearsEducation: phdSkills: ["Communication","Cross-functional collaboration","Technology transfer"]

Build and advance large-scale generative AI systems for physically accurate 3D worlds within Firefly Foundry. Develop novel 3D/4D generation pipelines (including mesh, materials, textures, reconstruction, lighting, animation, and simulation), agentic workflows, and synthetic data pipelines. Improve conditional generation and editing with strong evaluation across quality, efficiency, robustness, and safety, translating research into production-ready Python and modern ML implementations.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Adobe Systems
Adobe Systems
3 days ago

Staff Applied Scientist, 3D - Firefly Foundry

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: Just nowStatus: Live

Job Summary

Build and advance large-scale generative AI systems for physically accurate 3D worlds within Firefly Foundry. Develop novel 3D/4D generation pipelines (including mesh, materials, textures, reconstruction, lighting, animation, and simulation), agentic workflows, and synthetic data pipelines. Improve conditional generation and editing with strong evaluation across quality, efficiency, robustness, and safety, translating research into production-ready Python and modern ML implementations.
Location: San Jose, Seattle, San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Build novel generative models and pipelines for mesh/material/texture generation, scene reconstruction, lighting estimation, animation, and simulation.
  • •Develop agentic workflows to create, manipulate, repair, annotate, evaluate, and refine 3D and 4D content.
  • •Develop large-scale synthetic data pipelines using game/rendering engines, digital environments, 3D geometry, physically based materials, and simulation.
  • •Implement and rigorously evaluate conditional generation and editing techniques focused on instruction compliance, controllability, and visual quality.
  • •Collaborate across researchers, engineers, and product teams, and translate research into production-ready Python/ML implementations while maintaining evaluation pipelines.

Pay and Benefits

Salary: USD 164,000 - 313,300 annually

Key Requirements

  • •Ph.D. or MS in Computer Science, Machine Learning, Computer Graphics or a related field, with 8+ years industry experience.
  • •Extensive practical experience in large-scale generative AI training for image and video generation and editing.
  • •Experience with diffusion models, transformers, or other state-of-the-art generative architectures.
  • •Strong working knowledge of 3D content systems (meshes, materials, textures, scenes, cameras, lighting, coordinate systems, animation/motion workflows).
  • •Strong coding and prototyping skills in Python, PyTorch, and ML infrastructure tools.
Experience:8+ yearsGenerative AILarge-scale trainingImage generationVideo generationSynthetic data3D contentMultimodal
Education:PhD / Doctorate
Skills:CommunicationCross-functional collaborationTechnology transfer
Tech Stack:PythonPyTorchDiffusion modelsTransformersGame enginesRendering enginesML

Company Brief

Adobe Systems
Provides creative, marketing, and document management software and cloud services, including Photoshop, Illustrator, Acrobat, and the Adobe Experience Cloud, serving creative professionals, enterprises, and governments worldwide.
Industry: SaaS
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: San Jose, United States
Founded: 1982
Glassdoor
Glassdoor: 4.0
WebsiteLinkedInGlassdoor