The posting
※日本語版が続きます。
About AIRoA
AI Robot Association (AIRoA) is an organization dedicated to advancing the development of generative AI foundation models in the field of robotics by collecting large-scale real-world robot data, including data from humanoid robots.
AIRoA has been selected by Japan’s Ministry of Economy, Trade and Industry (METI) and NEDO under the “Post-5G Information and Communication Systems Infrastructure Enhancement R&D Project” to develop a data platform for generative AI foundation models in robotics. The project has a total budget of JPY 20.5 billion.
Leveraging this foundation, AIRoA is undertaking a project to collect one million hours of humanoid robot operation data using more than 100 robots, and to develop a world-class Vision-Language-Action (VLA) model based on this data.
Responsibilities
- Teleoperation Platform: Design and implement teleoperation systems for humanoid robots, mobile manipulators, and service robots, while continuously improving operability, stability, latency, and recovery performance.
- Demonstration Data Quality: Establish operation logs, sensor logs, failure classifications, reproduction procedures, and data collection workflows to improve the quality of human demonstrations used for imitation learning and VLA evaluation.
- Cross-Functional Collaboration: Work closely with the Autonomy, VLA, Simulation, Integration, and Hardware teams to ensure that teleoperation, control, testing, and real-world robot evaluation operate seamlessly as an integrated system.
- Real-Robot Debugging: Analyze logs related to low-latency communication, control cycles, sensor synchronization, abnormal states, and recovery behavior, and take ownership of reproducing, fixing, and verifying issues on real robots.
AIRoAについて
AI Robot Association（AIRoA）は、ヒューマノイドロボットをはじめとする実世界ロボットの⼤規模データを収集し、ロボティクス分野における⽣成AI基盤モデルの開発を推進する組織です。 AIRoAは、経済産業省およびNEDOの「ポスト5G情報通信システム基盤強化研究開発事業」において、ロボティクス分野の⽣成AI基盤モデル開発に向けたデータプラットフォーム開発の採択事業者に決定しており、事業予算は205億円です。この基盤をもとに、100台以上のロボットを⽤いて100万時間規模のヒューマノイドロボット操作データを収集し、それを活⽤して世界最⾼⽔準のVision-Language-Action（VLA）モデルを開発するプロジェクトを進めています。
業務内容
- テレオペレーション基盤: ヒューマノイド、モバイルマニピュレータ、サービスロボット向けのテレオペレーションシステムを設計‧実装し、操作性、安定性、遅延、復帰性を継続的に改善して頂きます。
- デモ収集品質: imitation learningやVLA評価に利⽤される⼈間デモの品質を⾼めるため、操作ログ、センサログ、失敗分類、再現⼿順、データ収集フローを整備して頂きます。
- クロスファンクショナル連携: Autonomy、VLA、Simulation、Integration、Hardwareチームと連携し、テレオペレーション、制御、テスト、実機評価が⼀貫して動作するように統合して頂きます。
- 実機デバッグ: 低遅延通信、制御周期、センサ同期、異常状態、復帰動作をログから解析し、実機で再現‧修正‧検証を担当頂きます。
Requirements
※日本語版が続きます。
Required Qualifications
- Hands-on experience controlling or debugging physical robotic systems, such as manipulators, humanoid robots, industrial robots, or service robots.
- Experience in teleoperation, including VR, haptics, force feedback, leader–follower systems, motion capture, puppeteering-based control, or real-time retargeting.
- Experience building robotic systems using ROS or ROS 2, including system integration and system-level analysis of physical robotic systems.
- Ability to persistently troubleshoot hard-to-reproduce issues on physical systems through iterative logging, hypothesis development, reproduction testing, fixes, and validation.
Preferred Qualifications
- Experience implementing robot control, real-time systems, communications, log analysis, or related tools in C or Python.
- Ability to develop systems with careful consideration of interfaces across multiple modules, such as sensors, control, state management, safety stops, UI, data collection, and evaluation environments.
- Experience with learning-based control, including imitation learning, reinforcement learning, hybrid MPC + learning, safety-constrained learning, or deployment of learned controllers.
- End-to-end experience in data collection, including human demonstration collection, operation quality evaluation, failure classification, task specification, evaluation set development, and collaboration with VLA or robot learning teams.
- Experience operating physical robotic systems in areas such as teleoperation, semi-autonomous operation, multi-robot operations, field testing, or long-duration testing.
- Experience with fleet management or production-grade robotic system operations.
必須要件
- マニピュレータ、ヒューマノイド、産業⽤ロボット、サービスロボット等のいずれかで、実機制御または実機デバッグの経験があること。
- テレオペレーションの経験（VR、haptics、force feedback、leader-follower、motion capture、puppeteering-based control、real-time retargeting）
- ROSまたはROS2を⽤いてロボットシステムを構築し、実機システムのシステム統合やシステム解析を⾏った経験があること。
- 実機で発⽣する再現性の低い問題に対して、ログ、仮説、再現実験、修正、検証を粘り強く回せること。
歓迎要件
- CまたはPythonで、ロボット制御、リアルタイムシステム、通信、ログ解析、または周辺ツールを実装した経験があること。
- センサ、制御、状態管理、安全停⽌、UI、データ収集、評価環境など、複数モジュールのインターフェースを意識して開発できること。
- 学習ベースでの制御に関わる経験（imitation learning、reinforcement learning、hybrid MPC + learning、safety-constrained learning、learned controller deployment）
- データ収集に関する⼀連の経験（⼈間デモ収集、操作品質評価、失敗分類、タスク仕様、評価セット構築、VLA/robot learningチームとの連携）
- 遠隔操作、半⾃律操作、複数ロボット運⽤、現場試験、⻑時間稼働試験など実機運⽤に関わる経験
- フリート管理や製品レベルでのシステム運⽤経験
Benefits
There are currently no comparable projects in the world that collect data and develop foundation models on such a large scale. As mentioned above, this is one of Japan’s leading national projects, supported by a substantial investment of 20.5 billion yen from NEDO.
This position will play a crucial role in determining the success of the project. You will have broad discretion and responsibility, and we are confident that, if successful, you will gain both a great sense of achievement and the opportunity to make a meaningful contribution to society.
Furthermore, we strongly encourage engineers to actively build their careers through this project—for example, by publishing research papers and engaging in academic activities.
Work location
Tokyo Ryutsu Center A Bldg. AW4-5/4-6, 6-1-1 Heiwajima, Ota-ku, Tokyo 143-0006, Japan
