Shield AI is a venture-backed defense-tech company with the mission of protecting service members and civilians with intelligent systems. Its products include Hivemind autonomy software, V-BAT and X-BAT aircraft, and Aechelon simulation and synthetic reality technologies. With offices and facilities across the U.S., Europe, the Middle East, and Asia-Pacific, Shield AI’s technology actively supports operations worldwide. For more information, visit www.shield.ai. Follow Shield AI on LinkedIn, X, Instagram, and YouTube.
Job Description:
Shield AI is seeking a Staff Engineer to help design, develop, and integrate a safety critical Run-Time Assurance (RTA) product. The Hivemind Foundations team is responsible for a suite of core products and capabilities that brings resilient autonomy and intelligence to aircraft and other platforms operating in complex environments. The RTA product that the Foundations team develops is a real-time safety capability that helps keep autonomy safe, predictable, and effective at the edge.
As a senior member of the Hivemind Foundations team, you will lead applied trajectory prediction and aircraft-response modeling for the RTA. You will work at the boundary between safety logic, vehicle state, and autopilot or flight-control APIs, turning aircraft performance data, command-response assumptions, and test evidence into predictive models that guide safe recovery behavior. You will evolve Trajectory Prediction Algorithm (TPA) models, validate them with Python, simulation, HIL, and flight-test data, and partner with C/C++ engineers to deliver reliable software that can fly, including support for X-BAT, Shield AI's flagship Group 5 Collaborative Combat Aircraft (CCA) UAV.
What you'll do:
Lead development, tuning, and validation of TPA and recovery-behavior models using aircraft performance data, command-response assumptions, 3DOF/6DOF flyout concepts, wind effects, uncertainty bounds, and maneuver constraints.
Build Python-based analysis, simulation, HIL, and flight-test workflows to compare predicted versus observed aircraft behavior, identify model gaps, tune parameters, and maintain regression datasets.
Integrate and evaluate trajectory-prediction behavior through off-the-shelf or custom autopilot interfaces, including command modes, vehicle-state inputs, latency, mode transitions, control limits, and telemetry analysis.
Support hardware integration and flight-test campaigns across relevant platforms; also help evolve trajectory-prediction and safety behaviors from single-aircraft use cases toward multi-agent collaborative CONOPS. Produce algorithm handoff artifacts and contribute scoped C/C++ implementation, testing, and debugging as needed.
Required qualifications:
Typically requires a minimum of 7 years of related experience with a Bachelor’s degree; or 6 years with a Master’s degree; or 4 years with a PhD; or equivalent work experience.
Deep experience in trajectory prediction, aircraft-response modeling, aerospace simulation, robotics, applied autonomy, or GNC-adjacent domains, including 3DOF and/or 6DOF aircraft modeling concepts.
Expert-level Python skills for algorithm development, numerical analysis, data processing, plotting, tuning workflows, and test automation.
Working proficiency in C or C++, with the ability to read production code, debug algorithm behavior, write tests, make scoped implementation changes, and guide software engineers through algorithm intent.
Demonstrated experience interfacing guidance, trajectory, or safety-critical algorithms with off-the-shelf or custom autopilots and validating behavior through simulation, HIL, flight hardware, or flight-test data.
Ability to document model assumptions, handoff artifacts, and validation evidence while leading technical coordination across algorithms, software, systems, test, and platform teams.
Preferred qualifications:
Experience tuning trajectory prediction, flyout, or vehicle-response models from simulation, HIL, or flight-test telemetry.
Experience implementing or porting algorithms from Python, MATLAB/Simulink, or prototype models into C or C++ production software.
Experience with Monte Carlo testing, scenario-based regression, validation metrics, envelope expansion, test-card planning, or flight-test safety reviews.
Familiarity with high-reliability or safety-critical development practices, such as static analysis, coding standards, traceability, requirements-based testing, and verification evidence.
Experience with CMake, Conan, Linux, CI/CD, embedded software workflows, or production software integration.
