Research Engineer / Scientist (SLAM)

Advanced Micro Devices, Inc•San Francisco, CA

About The Position

AMD is seeking a SLAM Specialist to design, implement, and advance state-of-the-art simultaneous localization and mapping systems for accurate, robust spatial understanding from real-world sensor data. The role focuses on modern classical and learning-based SLAM techniques, scalable state estimation, sensor fusion, and long-term mapping in complex, dynamic environments. This is a hands-on, research-driven position at the intersection of robotics, computer vision, and probabilistic inference. The successful candidate will collaborate with research scientists, machine-learning engineers, and systems teams to turn research advances into production-ready capabilities for AMD’s world modeling stack.

Requirements

  • At least 6 years of experience in SLAM, state estimation, robotics perception, or a related area.
  • Strong foundation in probabilistic estimation, optimization, and geometric vision, including techniques such as bundle adjustment, factor graphs, and Kalman filtering.
  • Deep experience with one or more SLAM paradigms: visual, visual-inertial, lidar, multi-sensor, or hybrid systems.
  • Proficiency in Python and/or C++, with hands-on experience building research- or production-grade SLAM systems.
  • Experience with numerical optimization libraries and/or robotics frameworks.
  • Strong understanding of real-world sensor characteristics, calibration, synchronization, and noise modeling.
  • Ability to work in ambiguous, fast-moving environments and drive projects from concept through deployment.
  • Engineering rigor and ownership, with a focus on correctness, stability, and measurable improvements.
  • Ability to collaborate effectively with a small, high-caliber team and contribute through thoughtful design, experimentation, and code quality.

Nice To Haves

  • Familiarity with learning-based perception or representation learning and how it can augment classical SLAM pipelines.

Responsibilities

  • Design and implement SLAM systems for real-world environments, including visual, visual-inertial, lidar, and multi-sensor configurations.
  • Develop localization and mapping pipelines covering pose estimation, map management, loop closure, and global optimization.
  • Research and prototype learning-based or hybrid SLAM approaches that combine classical geometry with machine-learning methods.
  • Build and maintain scalable state-estimation frameworks using factor-graph optimization, filtering, and smoothing techniques.
  • Develop sensor-fusion strategies integrating cameras, IMUs, depth sensors, lidar, or other modalities.
  • Analyze real-world SLAM failure modes, including perceptual aliasing, dynamic scenes, and drift, and develop principled solutions.
  • Create evaluation frameworks, benchmarks, and metrics for SLAM accuracy, robustness, and performance across large datasets.
  • Optimize real-time performance, memory usage, and compute efficiency for large-scale production systems.
  • Collaborate with reconstruction, simulation, and infrastructure teams to integrate SLAM outputs with downstream world-modeling and rendering pipelines.
  • Propose research ideas, mentor teammates, and help define organizational best practices for localization and mapping.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service