Figure
State Estimation Engineer - Data Collection Systems
San Jose, CAFrom $150kfull-timemidAdded today
About this role
Figure seeks a State Estimation Engineer to architect dual-tier sensor fusion pipelines for humanoid robot teleoperation and offline motion capture. You'll design real-time filters, batch optimization routines, and calibration workflows that fuse multimodal sensors to track full-body human kinematics and robot state.
What you'll do
- Design and implement dual-tier state estimation algorithms in C++: real-time filters for teleoperation and batch optimization for offline trajectory reconstruction
- Develop subject-calibration procedures to estimate body segment dimensions, joint offsets, and sensor extrinsics for individual users
- Build sensor fusion architectures combining spatial transforms, visual-inertial, and inertial data into kinematic pose estimates
- Address spatiotemporal calibration, environmental interference, and kinematic constraint enforcement on skeletal models
- Extract information from compliant tactile sensing under deformation and design diagnostic tooling and validation pipelines
- Evaluate novel sensing modalities and diagnose hardware limitations to inform future design requirements
What they're looking for
- Multi-sensor fusion and state estimation for dynamic systems
- Real-time filtering (EKF, sliding-window estimators)
- Batch optimization (Factor Graphs, GTSAM, Ceres, NLLS)
- 3D spatial kinematics, Lie groups (SE(3), SO(3)), forward/inverse kinematics
- C++ for embedded/edge computing platforms
- Python for data analysis and visualization
- Calibration and alignment workflow design
- Constrained optimization
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Figure
Figure develops advanced humanoid robots powered by AI technology. The company is hiring engineers across mechanical design, firmware development, manufacturing, quality assurance, and security to build and refine its autonomous robotic systems.
View all jobs at FigureLikely interview questions
- Walk us through your most complex multi-sensor fusion project—which sensors did you fuse, what challenges arose, and how did you validate accuracy?
- Describe your experience with both real-time filtering and batch optimization—when have you chosen one approach over the other and why?