About the job
About World Labs:
At World Labs, we are pioneers in developing foundational world models capable of perceiving, generating, reasoning, and interacting with the 3D world. Our mission is to unlock the full potential of AI through spatial intelligence, transforming vision into action, perception into reasoning, and imagination into innovation.
We envision a future where spatial intelligence opens new avenues for storytelling, creativity, design, simulation, and immersive experiences across virtual and physical realms.
Our team comprises top experts united by a shared curiosity and passion for technology, ranging from AI research to systems engineering and product design. This synergy creates a dynamic feedback loop between our state-of-the-art research and the products that empower our users.
Role Overview
We are seeking a SLAM Specialist to conceptualize, develop, and enhance cutting-edge simultaneous localization and mapping systems, ensuring accurate and resilient spatial understanding derived from real-world sensor data. Your focus will be on modern SLAM techniques, encompassing both classical and learning-based methodologies, with an emphasis on scalable state estimation, sensor fusion, and long-term mapping within complex, dynamic environments.
This role is hands-on and research-oriented, perfect for someone who thrives at the intersection of robotics, computer vision, and probabilistic inference. You will work closely with research scientists, ML engineers, and systems teams to translate advanced SLAM concepts into production-ready capabilities that serve as the backbone of our world modeling stack.
What You Will Do:
- Design and implement advanced SLAM systems for real-world scenarios, including visual, visual-inertial, lidar, or multi-sensor configurations.
- Develop robust localization and mapping pipelines, focusing on pose estimation, map management, loop closure, and global optimization.
- Research and prototype innovative learning-based or hybrid SLAM approaches that synergize classical geometry with contemporary machine learning techniques.
- Construct and maintain scalable state estimation frameworks, including factor graph optimization, filtering, and smoothing methodologies.
- Devise sensor fusion strategies that incorporate cameras, IMUs, depth sensors, lidar, or various modalities to enhance robustness and precision.
- Examine failure modes in real-world SLAM applications (e.g., perceptual aliasing, dynamic scenes, drift) and develop principled solutions.
- Create evaluation frameworks, benchmarks, and metrics to assess SLAM accuracy, robustness, and performance across extensive datasets.
- Optimize performance throughout the stack, including adherence to real-time constraints.
