Staff Engineer, State Estimation (dallas/san Diego/boston/dc/san Fran)

Shield AI Shield AI · Defense · Dallas, TX +4 · V-BAT Engineering - Software

Staff Engineer focused on state estimation and sensor fusion for autonomous UAVs in GPS-denied environments. Develops and implements real-time navigation algorithms, integrates multi-sensor data, and collaborates with autonomy and software teams to transition research into fielded capabilities.

What you'd actually do

  1. Develop and implement real-time state estimation algorithms including inertial navigation, sensor fusion, and alternative navigation methods for GPS-denied or degraded environments.
  2. Integrate data from IMUs, GNSS receivers, visual odometry, magnetometers, barometers, and radar into robust estimation frameworks.
  3. Design sensor processing pipelines focused on accuracy, robustness, and system-level fault tolerance.
  4. Collaborate with autonomy, software, and hardware teams to ensure end-to-end integration of navigation and PNT systems.
  5. Conduct simulation, lab testing, and field trials to evaluate algorithm performance under real-world conditions.

Skills

Required

  • 7+ years of relevant experience with a bachelor’s degree; or 6 years with a master’s degree; or 4 years with a PhD; or equivalent practical experience
  • Experience developing and deploying real-time navigation or sensor fusion algorithms using IMUs, GPS, or other sensors.
  • Strong understanding of filtering and estimation techniques (e.g., Kalman filters, EKF, UKF, particle filters).
  • Proficient in C++11 or newer in real-time environments.
  • Comfortable working in Linux, with experience using standard command-line tools and scripting.
  • Strong written and verbal communication skills with a collaborative mindset.
  • Demonstrated success working in fast-paced development cycles and delivering high-quality results.

Nice to have

  • Experience implementing inertial navigation algorithms in degraded or GPS-denied conditions.
  • Exposure to visual odometry or computer vision-based navigation approaches.
  • Experience optimizing code for performance on compute-constrained platforms.
  • Familiarity with CUDA or hardware acceleration techniques (e.g., FPGAs).
  • Experience transitioning navigation solutions from research into production environments.

What the JD emphasized

  • real-time
  • GPS-denied or degraded environments
  • robust estimation frameworks
  • system-level fault tolerance
  • real-world conditions
  • transitioning navigation solutions from research into production environments