Research Engineer / Scientist (SLAM)
$250k - $350k • San Francisco
Posted 20d ago
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
World Labs is a frontier AI research and product company focused on spatial intelligence, co-founded by Dr. Fei-Fei Li, Justin Johnson, and Ben Mildenhall. The company is pioneering world models that perceive, generate, reason, and interact with virtual and physical worlds, with its flagship product Marble transforming text, images, and video into navigable 3D worlds. Backed by leading investors, World Labs is assembling a world-class team at the intersection of AI research and real-world deployment.
Responsibilities
- Design and implement modern SLAM systems for real-world environments, including visual, visual-inertial, lidar, or multi-sensor configurations.
- Develop robust localization and mapping pipelines, including pose estimation, map management, loop closure, and global optimization.
- Research and prototype learning-based or hybrid SLAM approaches combining classical geometry with modern machine learning.
- Build and maintain scalable state estimation frameworks, including factor graph optimization, filtering, and smoothing techniques.
- Develop sensor fusion strategies integrating cameras, IMUs, depth sensors, lidar, or other modalities.
- Analyze SLAM failure modes in real-world deployments and design principled solutions.
- Create evaluation frameworks, benchmarks, and metrics to measure SLAM accuracy, robustness, and performance.
- Optimize performance across the stack for real-time constraints, memory usage, and compute efficiency.
- Collaborate with reconstruction, simulation, and infrastructure teams to ensure SLAM outputs integrate with downstream pipelines.
- Contribute to technical direction by proposing new research ideas, mentoring teammates, and defining best practices.
Requirements
- 6+ years of experience in SLAM, state estimation, robotics perception, or related areas.
- Strong foundation in probabilistic estimation, optimization, and geometric vision.
- Deep experience with one or more SLAM paradigms (visual, visual-inertial, lidar, multi-sensor, or hybrid systems).
- Proficiency in Python and/or C++ with experience building research or production-grade SLAM systems.
- Experience with numerical optimization libraries and/or robotics frameworks.
- Familiarity with learning-based perception or representation learning and its application to SLAM.
- Strong understanding of real-world sensor characteristics, calibration, synchronization, and noise modeling.
- Proven ability to work in ambiguous, fast-moving environments and drive projects from concept through deployment.
- Strong sense of ownership, engineering rigor, correctness, stability, and measurable improvements.
- Enjoy collaborating with a high-caliber team and raising the technical bar.