Helix AI Engineer, Localization and Mapping
At a glance
Mid-level AI Engineering role at Figure. San Jose · $200,000–$400,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Build real-time systems that combine camera, IMU, encoder and magnetic-sensor data for localization, motion tracking and state estimates
- Create offline pose-tracking workflows that can handle large training datasets from varied sources
- Develop and tune sensor calibration for humanoid robots and data-collection platforms
- Work with other teams on data-led evaluation and testing, then deliver reliable software for robotics in real settings
What you bring
- You can solve difficult estimation and nonlinear optimization problems and work confidently with 3D geometry, visual-inertial SLAM and computer vision
- You have practical experience calibrating sensors, including camera and IMU parameters
- You write efficient C++ software
- You can explore and iterate quickly when priorities or problems are unclear
Who this fits
This role suits an engineer focused on estimation, mapping and sensor calibration for robotics. The position is based in San Jose and is listed at mid-level seniority.
From the employer
Figure is an AI robotics company developing autonomous general-purpose humanoid robots. The goal of the company is to ship humanoid robots with human level intelligence. Its robots are engineered to perform a variety of tasks in the home and commercial markets. Figure is headquartered in San Jose, CA.
Figure’s vision is to deploy autonomous humanoids at a global scale. Our AI team is looking for Localization and Mapping Engineers to empower Figure humanoid robots to perform highly dynamic operations in demanding real-world environments.
Responsibilities:
-
Architect and implement real-time localization, ego-motion tracking, and state estimation systems by fusing multi-modal sensor data (cameras, IMUs, encoders, magnetic sensors).
-
Build and maintain scalable, offline pose-tracking pipelines to process large-scale training data from diverse sources.
-
Develop and optimize multi-sensor calibration systems for humanoid robotics and data collection platforms.
-
Partner with cross-functional teams to build comprehensive, data-driven evaluation and testing frameworks.
-
Design, engineer, and deploy high-quality, reliable software solutions for real-world robotics applications.
Requirements:
-
Deep technical expertise in solving complex estimation and nonlinear optimization problems.
-
Strong command of 3D geometry, visual-inertial SLAM, and computer vision techniques, including feature matching/tracking, and Structure from Motion (SfM).
-
Experience writing performant C++ software.
-
Hands-on experience with sensor calibration (e.g., multi-camera and IMU intrinsics/extrinsics).
-
Ability to thrive in a fast-paced, ambiguous environment that requires rapid exploration and iteration.
-
Passion for advancing humanoid robotics technology.
Bonus Qualifications:
-
Experience implementing visual-inertial SLAM systems on legged robotic platforms.
-
Background in estimation problems related to human motion capture or AR/VR applications.
-
Experience applying state-of-the-art Deep Learning approaches to SLAM, 3D reconstruction, or human pose estimation.
The US base salary range for this full-time position is $200,000 to $400,000 per year.
The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience. The total compensation package may also include additional components/benefits depending on the specific role. This information will be shared if an employment offer is extended.