REINFORCEMENT LEARNING

Hạn nộp hồ sơ đến ngày: 30/11/2024

Mục tiêu công việc

  • Conduct research and development of reinforcement learning algorithms, simulation environments, and sim2real techniques for training robots to perform specified tasks.
  • Research and develop new solutions for control problems related to motors, mechanisms, and other components in industrial, humanoid, and AGV robots.
  • Research, test, and evaluate PID, Fuzzy, and other controllers on various robot motors in Matlab-Simulink and other environments. Implement algorithms, tune parameters, and test system performance.
  • Research and apply motion control methods for Servo and BLDC motors, including sliding mode control, adaptive control, and other techniques.
  • Collaborate closely with team members to ensure the quality and progress of projects.
  • Prepare reports on project results and propose improvements.

Yêu cầu

For Junior:

  • Bachelor's degree in Computer Science, Information Technology, Robotics, Automation, Mechatronics, or a related field.
  • Foundational knowledge of AI and Robotics.
  • Understanding of reinforcement learning algorithms (DQN, PPO, SAC, etc.) and imitation learning algorithms (BC, AIRL, DAgger, etc.) for training robots in simulated environments.
  • Experience using one of the following robot simulation environments: Mujoco, Pybullet, IsaacGym, etc.
  • Experience in control theory, including PID control, parameter evaluation, and application to real robot manipulators.
  • Experience using at least one common programming language (Python, Java, C++, etc.).
  • Excellent English reading comprehension skills, research skills, and problem-solving abilities.
  • Strong sense of responsibility, proactive work attitude, and excellent teamwork skills.
  • Preferred: Experience in transferring from simulation to reality for robots and foundation models for robots.

For Senior:

  • 4+ years of experience working with industrial and civilian robot models.
  • Strong programming skills and experience using development tools.
  • Extensive experience in reinforcement learning algorithms (DQN, PPO, SAC, etc.), imitation learning algorithms (BC, AIRL, DAgger, etc.), hierarchical reinforcement learning, and foundation models for training robots to perform tasks.
  • Proficiency in one of the following robot simulation environments: Gazebo, Mujoco, Rviz, Pybullet, IsaacGym, ROS/ROS2, etc.
  • Experience in transferring from simulation to real robot operation (sim2real).
  • Excellent communication skills, teamwork skills, and leadership skills, and the ability to collaborate with members of Vision and Mechanical teams.
  • Preferred: Experience with robot motor control protocols/protocols: CAN, TCP-IP, Modbus, Serial, etc.
  • Preferred: Understanding of PID algorithms and proficiency in Matlab-Simulink.
  • Preferred: Candidates with experience in motion control for Servo and BLDC motors and their control methods.

Quyền lợi

  • Competitive salary upto 1800$/month.
  • Professional, dynamic, and friendly work environment.
  • Opportunity to participate in international projects and learn new skills.
  • Continuous training and professional development opportunities.
  • Comprehensive benefits package in accordance with company and government regulations.
  • Opportunity for career advancement and development within the company.

Để ứng tuyển, hãy gửi cho chúng tôi

  • Horus AI Co., Ltd.
  • Address: VOV residential area, Me Tri, Nam Tu Liem, Hanoi.
  • Email: [email protected]

We are recruiting...