State Estimation Engineer - Data Collection Systems
Figure is an AI robotics company developing general-purpose humanoid robots and its Helix vision-language-action AI system.
Funding history
About Figure
Figure develops and deploys general-purpose humanoid robots for commercial and household tasks. Its current Figure 03 robot is powered by Helix, an onboard generalist vision-language-action model; the company also operates the Index data-collection service.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and deploy real-time and offline state-estimation pipelines for teleoperation and trajectory reconstruction. You will develop calibration routines, fuse sensor data into human kinematic pose estimates, address sensor calibration and constraints, evaluate sensing approaches, and build tooling to validate algorithm accuracy.
Requirements
- 4+ years of multi-sensor fusion and state-estimation experience for dynamic hardware systems
- Real-time filtering including EKFs and sliding-window estimators
- Offline batch optimization including factor graphs, GTSAM, Ceres, and nonlinear least squares
- Calibration, zeroing, and alignment workflows for multi-sensor suites and kinematic models
- 3D spatial kinematics
- Lie groups including SE(3) and SO(3)
- Forward and inverse kinematics
- Constrained optimization
- C++
- Embedded or edge computing
- Python
- Data analysis
- Data visualization
Responsibilities
- Design and implement real-time filtering and offline optimization state-estimation algorithms in C++
- Develop subject-calibration procedures for body dimensions, joint offsets, and sensor-to-body extrinsics
- Develop sensor-fusion architectures for full-body kinematic pose estimates
- Address spatiotemporal sensor calibration, environmental interference, and kinematic constraints
- Extract useful information from compliant tactile sensing
- Diagnose hardware limitations and inform future design requirements
- Evaluate novel sensing modalities
- Build diagnostic tooling, validation pipelines, and error-analysis workflows