Reinforcement Learning Engineer

Job Description

VinRobotics, based in Hanoi, Vietnam, is revolutionizing corporate operations with a fleet of autonomous robots addressing labor shortages and challenging tasks. Join our in-office team to help bring our vision of deploying autonomous robots to solve real-world problems.

We are seeking multiple Reinforcement Learning Engineers to lead the development, training, and deployment of reinforcement learning (RL) algorithms for robots. You will play a pivotal role in advancing locomotion and manipulation capabilities by developing scalable simulation and training infrastructure, ensuring that our robots operate effectively in real-world environments.

Key Responsibilities:

• Develop, train, and deploy reinforcement learning algorithms for robotic motion and manipulation tasks.

• Build and optimize simulation infrastructure to support large-scale policy training for general-purpose robots.

• Collaborate with the controls team to integrate/distill learned MPC policies into the RL stack.

• Define performance metrics, test learned policies, and evaluate their effectiveness in real-world scenarios.

Required Qualifications:

• Proficiency in writing production-quality code using PyTorch/Tensorflow/JAX.

• Familiarity with online and offline RL algorithms, such as PPO and SAC.

• Familiarity with simulation technologies  (e.g., Gazebo, IsaacSim, NVIDIA Omniverse IsaacLab, Mujoco, Bullet)

• Experience in tuning hyperparameters, designing cost functions, and optimizing RL training processes.

• Knowledge of RL techniques, including domain randomization, curriculum learning, and reward shaping.

• Familiarity with machine learning evaluation tools like TensorBoard or Weights & Biases.

Preferred Qualifications:

• Experience in transferring policies learned in simulation to real robot hardware.

• Hands-on experience with massive parallelization training frameworks such as IsaacGym/IsaacLab

• Hands-on experience in training locomotion policies for quadrupedal or bipedal robots.

• Proven experiences with RL applications in industry or real-world problems.