Pipeline Engineer (Graphics/3D)

We build foundational world models that can perceive, generate, reason, and interact with the 3D world — unlocking AI's full potential through spatial intelligence by transforming seeing into doing, perceiving into reasoning, and imagining into creating.  We believe spatial intelligence will unlock new forms of storytelling, creativity, design, simulation, and immersive experiences across both virtual and physical worlds. We bring together a world-class team, united by a shared curiosity, passion, and deep backgrounds in technology — from AI research to systems engineering to product design — creating a tight feedback loop between our cutting-edge research and products that empower our users. Role Overview We are building a production-grade web application for 3D Gaussian Splat scene generation, editing, and publishing , and we’re looking for a Pipeline Engineer to help integrate cutting-edge research features and make them reliable, debuggable, and delightful to use. This is a high-ownership, fullstack-but-backend-heavy role that sits between R&D and frontend . You will work end-to-end across graphics/ML algorithms, backend services, and frontend UI — turning proof-of-concepts into shipped features that users can rely on. The ideal candidate enjoys making complex, messy systems work smoothly in production and improving them continuously based on both internal testing and external user feedback. Key Responsibilities Bridge research and product by working closely with both graphics/computer vision researchers and frontend engineers to ship usable features. Turn standalone Python scripts into clean, production-ready systems with clear inputs, outputs, validations, and failure modes. Develop backend services, APIs, and tooling that expose complex 3D workflows in a reliable and scalable way. Assist in integrations across the 3D ecosystem, including asset import/export and format conversion with common DCC tools. Ideal Candidate Profile You have a strong pipeline mindset , with experience turning scripts into production systems with clear inputs, outputs, validations, and failure modes. You enjoy building tools and infrastructure that enable others, and you take pride in making complex systems understandable and usable. You have fluency in the 3D ecosystem , including familiarity with 3D algorithms, DCC tools and common 3D file formats, sufficient to design integrations and debug workflow issues. Minimum Qualifications Strong proficiency in Python , including packaging, typing, tooling, debugging, and performance profiling. Strong literacy in core  3D graphics and computer vision concepts , such as transforms, cameras, coordinate systems, rendering, and visual artifact debugging. Demonstrated experience taking prototypes to production, including refactoring, testing, CI/CD, versioned artifacts, and reproducibility. Solid backend fundamentals, including HTTP APIs, FastAPI (or similar frameworks), async/concurrency basics, cloud deployment, and service reliability. Strongly Preferred / Nice-to-Haves Experience with photogrammetry, 3D reconstruction, or Gaussian splat rendering pipelines . Hands-on experience with DCC tools such as  Blender, Maya, Houdini, Unreal, or Unity . Familiarity with the GPU stack ( CUDA, PyTorch) , batch/queue systems, and containerization (Docker, Kubernetes). Frontend adjacency, with comfort collaborating on  React-based parameter plumbing and UX for technical controls. Experience with production pipelines at  VFX, animation, or gaming studios. A production support mindset, including willingness to iterate on documentation, tutorials, and error messages to improve usability and reduce misuse. Example Projects You Might Work On Packaging ML and 3D Python pipelines into GPU-backed FastAPI services with request validation, reproducible outputs, and well-defined request/response schemas. Designing parameter schemas and defaults that map cleanly from frontend controls to backend APIs and internal pipeline configurations. Integrating import/export workflows with popular DCC tools (e.g., Blender, Maya, Houdini, Unity, Unreal, USD), identifying workflow friction, and producing lightweight documentation, tutorials, and example code/scripts to help users succeed. Who You Are: Fearless Innovator: We need people who thrive on challenges and aren't afraid to tackle the impossible. Resilient Builder: Impacting Large World Models isn't a sprint; it's a marathon with hurdles. We're looking for builders who can weather the storms of groundbreaking research and come out stronger. Mission-Driven Mindset: Everything we do is in service of creating the best spatially intelligent AI systems, and using them to empower people. Collaborative Spirit: We're building something bigger than any one person. We need team players who can harness the power of collective intelligence.   We're hiring the brightest minds from around the glob