{"id":81525,"title":"Dynamics, System Identification & Estimation Engineer - PLA (human)","company":"Neura Robotics","city":null,"region":"Baden-Württemberg","location":"Metzingen / Riederich, Riederich, Baden-Wurttemberg, Germany","work_model":"onsite","employment_type":"full_time","employment":["full_time"],"roles":["software"],"visa":"not_mentioned","relocation":"not_mentioned","posted_at":"2026-06-01T16:14:30.524000+00:00","tools":["C++","Python"],"seniority":"mid","years_experience_min":4,"german_requirement":"not_mentioned","german_level":"unspecified","english_requirement":"required","english_level":"unspecified","team_language":"unknown","confidence":0.4,"method":"rules","language_badge":"Not stated","language_evidence":null,"requirements_snippet":"Humanoid or legged robot hands-on experience — 4NE1 is a full-size humanoid; bipedal dynamics and contact complexity are directly relevant Differentiable simulators for gradient-based system identification (Brax, DiffTaichi, or …","url":"https://jobs.ashbyhq.com/neura-robotics-gmbh/6e94e373-b040-4cc3-8ffc-677b7239c2a2","source":"ashby","agency":null,"description_text":"Your Mission & Challenges\n• Dynamic model accuracy ownership: defining model fidelity metrics and owning the gap between simulation behaviour and real-hardware behaviour across dynamic motion and contact-rich interactions\n• System identification on 4NE1 hardware: motor constants, joint friction, transmission dynamics — excitation trajectory design, regressor fitting, observability analysis, iterative refinement against hardware data\n• Simulation model authoring and maintenance: MuJoCo and Isaac Sim models that match real-world behaviour under dynamic loading and contact; contact model parameterisation, actuator model calibration\n• Real-time state estimation: floating-base EKF/UKF implementation and tuning for pelvis pose, velocity, and foot contact state at RT loop rates; feeds downstream controllers and loco-manipulation policy inputs\n• Sim-to-real pipeline: parameter estimation loops, hardware-data-driven calibration, validation against motion capture or external reference systems — the continuous feedback loop between hardware campaigns and updated sim models\n• Failure mode ownership: debugging model-accuracy-driven failures — control instability from inaccurate dynamics, estimation drift or bias causing divergence, incorrect contact/force estimation leading to instability in dynamic interactions\n• Cross-team interface: supplying updated Pinocchio model parameters to the WBC and State Estimation Engineers in Core Robot Software; aligning on excitation trajectory designs with the Locomotion and RL/Control Engineers\n\nWhat we can look forward to\n• MSc or PhD in Robotics, Mechanical Engineering, Electrical Engineering, or a related field with a strong foundation in dynamics, estimation, and control\n• 4+ years of experience developing state estimation or system identification solutions for real-time robotic systems — on real hardware, not simulation-only\n• System identification on physical robotic systems: excitation trajectory design, least-squares or maximum-likelihood regressor fitting, actuator and transmission parameter identification\n• State estimation implementation: EKF or UKF for floating-base pose, velocity, and contact state on a legged or mobile robot platform\n• Rigid body dynamics depth: contact modelling, actuator behaviour, and how model inaccuracies propagate to control instability — not just theoretical familiarity\n• Experience supporting control systems (MPC, WBC) or learned policies (RL) through hardware deployment — understanding how model quality gates policy transfer\n• C++ for production RT systems; Python for analysis, tooling, and calibration pipelines\n\nNice to Have\n• Humanoid or legged robot hands-on experience — 4NE1 is a full-size humanoid; bipedal dynamics and contact complexity are directly relevant\n• Differentiable simulators for gradient-based system identification (Brax, DiffTaichi, or comparable)\n• Sim-to-real transfer methodology: domain randomisation, adaptive calibration, residual physics modelling\n• Pinocchio for rigid-body model computation and parameter sensitivity analysis\n• MuJoCo model authoring: MJCF contact parameters, actuator models, tendon dynamics\n• Factor graph-based estimation (GTSAM, iSAM2) for tightly-coupled IMU + kinematics fusion\n• Publications or open-source contributions in legged robot dynamics, system identification, or sim-to-real transfer","responsibilities_text":null,"requirements_text":"• Humanoid or legged robot hands-on experience — 4NE1 is a full-size humanoid; bipedal dynamics and contact complexity are directly relevant\n• Differentiable simulators for gradient-based system identification (Brax, DiffTaichi, or comparable)\n• Sim-to-real transfer methodology: domain randomisation, adaptive calibration, residual physics modelling\n• Pinocchio for rigid-body model computation and parameter sensitivity analysis\n• MuJoCo model authoring: MJCF contact parameters, actuator models, tendon dynamics\n• Factor graph-based estimation (GTSAM, iSAM2) for tightly-coupled IMU + kinematics fusion\n• Publications or open-source contributions in legged robot dynamics, system identification, or sim-to-real transfer","status":"open","duplicate_of":null,"first_seen":"2026-11-04T00:18:17.446406+00:00","responsibilities_summary":null,"requirements_summary":null,"all_tools":["C++","Python"],"posting_language":"en","evidence":[],"years_experience_max":null,"mobility_evidence":[],"model_version":"rules-8","english_badge":"English required","company_id":2275}