[R&D]Research Scientist - Control/Reinforcement Learning
Reazon Holdings
On-site
Japan
Laboratory Scientist
About Enactic
"Bringing autonomous humanoid companions into homes worldwide to assist and enhance our daily lives" Enactic is a deeptech startup on a mission to ship assistive humanoid robots that enhance our independence and quality of life in a world facing critical labor shortages, due to aging demographics.
Responsibilities
As our Controls and Reinforcement Learning Research Scientist, will be responsible for developing high-performance, reliable control systems for robots, including designing, implementing, and tuning motion-control algorithms that enable real robots to acquire advanced motion skills. Leveraging principles from control theory, reinforcement learning, and multimodal AI models, you will build controllers that balance robustness, adaptability, and real-world feasibility. You will iteratively validate and refine these algorithms in both simulation environments and on real hardware, continuously elevating system performance. You will also collaborate closely with hardware, firmware, and AI model development teams to create practical, end-to-end solutions that span robot design, control architectures, learned policies, and deployment on physical robots.
Requirements
・Build motion control systems that perform in real-world environments using our robot platform, leveraging reinforcement learning and iterative experimentation ・Production-grade development experience in C/C++, Python, Docker, Linux, and Git ・Expertise in robotics and control engineering, with specialization in reinforcement learning control ・Experience with robot simulation and real hardware integration (Isaac Sim, MuJoCo, etc.) ・3+ years of research or development experience in robotics AI or related fields
Bonus Qualifications
・Proficiency in RL techniques including domain randomization, curriculum learning, and reward design ・Knowledge of simulation optimization and safety assurance for deploying RL on real robots ・Experience with sensor fusion and state estimation ・Knowledge and implementation experience with force estimation, collision detection, and compliance control ・Deep understanding of humanoid mechanics, actuator control, and sensor integration ・Deep understanding of mechanical engineering, motor characteristics, and drive/transmission mechanisms ・Track record researching and developing cutting-edge algorithms for robot perception, dexterous manipulation, planning, and reasoning ・Led advanced AI or robotics projects from R&D through stable real-world deployment
"Bringing autonomous humanoid companions into homes worldwide to assist and enhance our daily lives" Enactic is a deeptech startup on a mission to ship assistive humanoid robots that enhance our independence and quality of life in a world facing critical labor shortages, due to aging demographics.
Responsibilities
As our Controls and Reinforcement Learning Research Scientist, will be responsible for developing high-performance, reliable control systems for robots, including designing, implementing, and tuning motion-control algorithms that enable real robots to acquire advanced motion skills. Leveraging principles from control theory, reinforcement learning, and multimodal AI models, you will build controllers that balance robustness, adaptability, and real-world feasibility. You will iteratively validate and refine these algorithms in both simulation environments and on real hardware, continuously elevating system performance. You will also collaborate closely with hardware, firmware, and AI model development teams to create practical, end-to-end solutions that span robot design, control architectures, learned policies, and deployment on physical robots.
Requirements
・Build motion control systems that perform in real-world environments using our robot platform, leveraging reinforcement learning and iterative experimentation ・Production-grade development experience in C/C++, Python, Docker, Linux, and Git ・Expertise in robotics and control engineering, with specialization in reinforcement learning control ・Experience with robot simulation and real hardware integration (Isaac Sim, MuJoCo, etc.) ・3+ years of research or development experience in robotics AI or related fields
Bonus Qualifications
・Proficiency in RL techniques including domain randomization, curriculum learning, and reward design ・Knowledge of simulation optimization and safety assurance for deploying RL on real robots ・Experience with sensor fusion and state estimation ・Knowledge and implementation experience with force estimation, collision detection, and compliance control ・Deep understanding of humanoid mechanics, actuator control, and sensor integration ・Deep understanding of mechanical engineering, motor characteristics, and drive/transmission mechanisms ・Track record researching and developing cutting-edge algorithms for robot perception, dexterous manipulation, planning, and reasoning ・Led advanced AI or robotics projects from R&D through stable real-world deployment