Software Engineer- Spatial Media and Graphics, Vision Products Software - Jobs - Careers at Apple
- Develops machine learning techniques that generate spatial media experiences, such as Spatial Scenes, from photos and videos.
- Designs, trains, and evaluates models that predict 3D scene representations, such as 3D Gaussian splats, from a single image, a few views, or video.
- Applies generative models, such as diffusion models, to create plausible content and improve the realism of generated scenes.
- Develops rendering techniques for spatial media and works with graphics engineers to make them fast, stable, and visually robust on device.
- Builds data and evaluation pipelines, including synthetic data, perceptual quality metrics, and structured visual review, for problems where ground-truth novel views are rarely available.
- Partners with cross-functional teams to integrate new techniques into shipping features and see them through to release.
- Bachelor's degree in Computer Science, Electrical Engineering, or a related field and 3+ years of relevant industry or research experience.
- Hands-on experience designing, training, and evaluating deep learning models for computer vision or graphics tasks.
- Hands-on experience with 3D Gaussian splatting, such as per-scene optimization, feed-forward prediction, or custom rasterization.
- Hands-on experience training or fine-tuning diffusion or other generative models for images, video, or 3D content.
- Strong understanding of multi-view geometry and camera models, and of how 3D representations are rendered, including rasterization, alpha compositing, and volume rendering.
- Proficiency in Python and PyTorch, JAX, or MLX.
- Familiarity with C++, Objective-C, or Swift
- Familiarity with Gen AI coding tools. Demonstrated ability to use them for design, code generation, and debugging.
- MS or PhD in Computer Science, Electrical Engineering, or a related field.
- Experience with novel view synthesis or 3D reconstruction from images or video, such as monocular depth estimation, NeRFs, multiplane images, or dynamic scene reconstruction.
- Experience with real-time rendering or GPU programming (Metal, CUDA, or compute shaders), such as writing custom rendering kernels.
- Experience optimizing models for on-device inference, such as quantization, distillation, and Core ML.
- Experience with large-scale distributed training and building datasets, including rendering synthetic training data.
- Familiarity with stereo and spatial media, including metric scale and viewing comfort, or with AR/VR rendering pipelines.
- Track record of taking ideas from prototype to a shipped product or widely used project.
- Clear communication and the ability to collaborate across ML, graphics, and product teams.
Apple is an equal opportunity employer that is committed to inclusion and diversity. We seek to promote equal opportunity for all applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, Veteran status, or other legally protected characteristics. Learn more about your EEO rights as an applicant
At Apple, we believe accessibility is a fundamental human right. You’ll find that idea reflected in everything here — in our culture, our benefits and our digital tools. By welcoming as many perspectives as possible, we help you build a career where you feel like you belong.
Learn about accessibility in Apple’s workplace
Learn about reasonable accommodations for job applicants
Apple accepts applications to this posting on an ongoing basis.
Required Skills
Required Languages
🇬🇧 English