Robotics Reliability Engineer

About the role

The AI Robot Association (AIRoA) is building a data platform for generative AI foundation models in robotics, supported by a 20.5 billion yen project funded by METI and NEDO. It is collecting one million hours of humanoid robot operation data with more than 100 robots and developing a Vision-Language-Action (VLA) model. This Reliability Engineer role is based in Tokyo and focuses on deploying robots in the field, diagnosing incidents and improving quality and maintainability.

Key responsibilities

• Deploy and commission physical robots: install, configure, run trial runs, obtain site acceptance, create checklists and recovery procedures, and manage operations at deployment sites.
• Respond to incidents: diagnose and isolate software, network, sensor, actuator, power, mechanical and environmental issues, give first response and help prevent recurrence.
• Analyze logs and perform root cause analysis: use ROS/ROS 2 logs, system logs, sensor logs, operation logs, error codes and video recordings to document causes, reproduction conditions, impact, temporary and permanent fixes.
• Give the Engineering team feedback to improve quality, repairability, operability, user experience and on-site safety.
• Develop deployment, maintenance and troubleshooting procedures, checklists, work standards and workflows so the team can operate consistently.

Required profile

• Hands-on troubleshooting experience with physical systems such as robots, industrial automation equipment, mechatronic products, factory automation equipment or mobile robots.
• Experience analyzing logs and isolating faults in physical systems, and designing improvements through resolution.
• Ability to document reproduction steps, root-cause hypotheses, response history and improvement requests in a way engineers understand.
• Experience with on-site deployment, testing, adjustment, recovery, stakeholder coordination and safety procedures, or an equivalent practical approach.
• Ability to work with Hardware, Software, Integration, Simulation, Operations and other teams and turn field issues into technical challenges.
• Business-level Japanese.

Required skills

• Preferred: ROS/ROS 2, bag/log analysis, state machines, remote monitoring, OTA, diagnostic tools, health checks, anomaly detection.
• Preferred: RCA, FMEA, FRACAS, MTBF/MTTR, maintainability design, quality improvement, failure classification, recurrence prevention.
• Preferred: knowledge of motors, gearboxes, sensors, actuators, electrical systems, industrial networks, robotic arms or material-handling equipment.
• Preferred: multi-robot operations, fleet management, field operations, customer-site deployments, maintenance partner management, and industrial or robot safety.