Simulation & Digital Twin Engineer
Pubblicato il 15-10-2026 - Oversonic Robotics in Monza
Responsible for supporting the development, testing, and validation of high-fidelity simulation environments and digital twins for humanoid robotics. The role focuses on creating physically accurate assets, robot and sensor models, and complex simulated missions for feasibility studies. It supports simulation-to-real validation, reinforcement learning pipelines, synthetic data generation, and collaboration with simulation, mechanical, control, perception, and AI teams. Responsibilities * Test simulated environments and validate them against real-world scenarios. * Develop physically accurate assets from CAD models or 3D scans and integrate them into USD-based environments. * Support synthetic data generation pipelines for perception, testing, and learning. * Enable rapid simulation cycles by: Structuring environments for RL compatibility, optimizing simulation performance for scalability and parallel training. * Develop complex missions and scenarios for feasibility studies and system validation. * Support the design, integration, testing, and validation of new simulated robot models.
* Configure and validate simulated sensors, including LiDARs, cameras, IMUs, and force sensors. * Contribute to sim-to-real alignment and simulation documentation. Requirements * Degree in Mechanical Engineering, Robotics, Mechatronics, Automation or related field. * Experience in robotics simulation, physics-based environments, game engines, CAD, or 3D modelling. * Working knowledge of Python. * Experience with simulators such as Isaac Sim, MuJoCo, CATIA, Unity or similar. * Familiarity with: simulation pipelines, assets, scenes, and sensor simulation, CAD models and 3D environments, basic rendering and physics concepts, structured testing and validation. Nice to Have * Experience with USD/Omniverse ecosystem. * Exposure to synthetic data generation. * Familiarity with robot kinematics and dynamics or mechanical modelling. * Experience with Reinforcement Learning. * Familiarity with R