19 days ago
San Jose, CA, USAMid Level
Base Salary
$150k - $300k/yr
Responsibilities
- Design and implement real-time filtering and offline batch optimization state-estimation algorithms in modern C++.
- Own calibration workflows for body dimensions, joint offsets, and sensor-to-body extrinsics.
- Develop sensor-fusion architectures for full-body kinematic pose and floating-base motion estimation.
- Address spatiotemporal calibration, environmental interference, and kinematic constraints on human skeletal models.
- Extract information from deformable tactile sensors and evaluate novel sensing modalities.
- Diagnose hardware limitations and inform future hardware design requirements.
- Build diagnostic tools, validation pipelines, and error-analysis workflows for online and offline algorithms.
Requirements
- 4+ years of experience building multi-sensor fusion and state-estimation solutions for dynamic hardware systems.
- Hands-on expertise with real-time filtering techniques including EKFs and sliding-window estimators, plus offline batch optimization tools such as Factor Graphs, GTSAM, Ceres, and Non-Linear Least Squares.
- Experience designing calibration, zeroing, and alignment workflows for multi-sensor suites and kinematic models.
- Deep knowledge of 3D spatial kinematics, Lie groups including SE(3) and SO(3), forward and inverse kinematics, and constrained optimization.
- Ability to write high-performance modular C++ for embedded or edge platforms and Python for data analysis and visualization.
- Experience with low-latency teleoperation, haptics, or human-in-the-loop control systems is a bonus.
- Background in human biomechanics, skeletal tracking, or body-mounted telemetry systems is a bonus.
- Experience applying machine learning to motion priors, trajectory smoothing, or learned state estimation and calibration is a bonus.
Benefits
- Full-time position requiring five days per week of in-office collaboration in North San Jose, California.