We are seeking a Senior Researcher to join our LTX Render Lab at our company. This team is responsible for developing cutting-edge 3D technology to power state of the art video generation, enabling immersive and dynamic content creation. As a key member of the team, you will lead research efforts in 3D reconstruction, dynamic scene interaction, and multi-view video consistency, driving the transition from early prototypes to scalable, prodution-ready solutions.
What you will be doing
Conduct applied research in 3D reconstruction, scene creation, and animation.
Develop algorithms for placing characters and objects dynamically within 3D spaces.
Explore multi-view video consistency and advanced camera control for scene animation.
Optimize research code for scalability and real-time performance.
Collaborate with engineers, designers, and product managers to integrate 3D capabilities into user-facing features.
Stay up to date with cutting-edge academic research and apply relevant innovations to production.
Write high-quality code, ensuring research solutions are optimized for real-world applications.
Mentor junior researchers and contribute to knowledge-sharing initiatives within the team.
Requirements: M.Sc with 5+ years of industry experience in computer graphics or computer vision.
Strong expertise in 3D geometry, rendering pipelines, and computer vision (e.g., multi-view geometry, neural radiance fields, point-based rendering).
Deep understanding of modern AI/ML image/video generation and reconstruction techniques.
Proficiency in Python and/or C++ for high-performance algorithm development.
Experience transitioning proof-of-concept research into scalable production-ready solutions.
Strong ability to collaborate with interdisciplinary teams and communicate complex research findings effectively.
Preferred Requirements
Experience with game engines (Unreal, Unity) or 3D libraries (Panda3D, Three.js).
Familiarity with Gaussian splatting, neural rendering, and dynamic scene construction.
Prior experience with character animation, rigging, or AR/VR applications.
Understanding of cloud-based infrastructure for large-scale training or real-time inference.
This position is open to all candidates.