Company Description
At Owl3D, we're on a mission to revolutionize entertainment by bringing premium 3D video experiences to everyone. Our cutting-edge AI technology transforms beloved content—like movies, Netflix shows, and YouTube videos—into immersive 3D adventures for VR headsets, Apple Vision Pro, and our custom 3D hardware. Founded by industry veterans from Meta and Apple, our team thrives on innovation, continuous learning, and hands-on problem-solving. If you're passionate about pushing the boundaries of technology and entertainment, Owl3D is the place for you.
About the Role
We're seeking an experienced Research Engineer to lead the exploration of new methods to achieve real-time 3D processing.
Research areas like depth estimation, video inpainting, video interpolation, video generation, optical flow, object detection, segmentation, and super-resolution are all highly relevant.
You'll design and build a performant solution that serves as the foundation of all the products we build.
Key Responsibilities
- Lead Core Research Initiatives:
Drive the development of cutting-edge machine learning and computer vision models that enable real-time 3D video processing, depth estimation, and spatial reasoning. - Prototype and Iterate Quickly:
Build experimental systems to evaluate novel techniques in depth prediction, view synthesis, scene inpainting, and 3D video consistency. - Optimize for Real-Time Performance:
Profile, optimize, and accelerate neural network inference on various hardware targets (Nvidia, AMD, Apple Silicon). - Stay at the Frontier:
Continuously explore emerging research in vision, diffusion models, and generative video to inform Owl3D's technology roadmap. - Mentor and Guide:
Provide technical mentorship to junior researchers and engineers, fostering a culture of curiosity, rigor, and creativity.
Desired Qualifications & Experience:
Proven experience in one or more of the following areas:
Depth estimation and 3D reconstruction
Optical flow and video frame interpolation
Object segmentation and scene understanding
Image/video inpainting or generative modeling (diffusion, GANs, transformers)
Video super-resolution and enhancement
Strong Engineering Skills:
Proficiency in PyTorch or TensorFlow; experience building and deploying models in production environments.- Systems & Optimization:
Solid understanding of GPU acceleration, CUDA optimization, model quantization, and real-time inference techniques. - Research Acumen:
Track record of publications in top-tier ML/CV conferences (CVPR, ICCV, NeurIPS, etc.) or demonstrated contributions to open-source projects. - Cross-Disciplinary Thinking:
Ability to combine visual computing, deep learning, and human perception principles to create realistic 3D experiences.
Why Join Owl3D?
At Owl3D, you'll have the opportunity to:
- Shape the Future: Lead the development of our cutting-edge 3D AI pipeline, directly influencing the next generation of entertainment.
- Tackle Big Challenges: Work at the intersection of software, hardware, and AI, solving unique problems in multimedia and system design.
- Grow and Innovate: Enjoy autonomy, mentorship opportunities, and the chance to push the boundaries of technology in a dynamic startup environment.
- Make an Impact: Play a key role in building a product that redefines how people experience 3D content. If you're excited to build innovative technology and create immersive experiences, we'd love to hear from you. Join us at Owl3D and help transform the world of entertainment