Humanoid Robotics RL/IL Learning Engineer

Oversonic Robotics Srl; Milano; Hybrid; EUR 55,000 - 90,000; Full time

Benefits offered by this job

Hybrid work environment

Smart Working: 1 day/week

Job summary

Oversonic Robotics Srl is seeking a researcher to develop learning-based control strategies for humanoid robots. You will build training pipelines, design diverse task environments, and manage experiments from simulation to real-world validation.

The role requires strong Python and PyTorch skills, experience with RL algorithms, and a proven ability to translate learning into reliable robot behaviors while addressing sim-to-real challenges.

Qualifications

• MS/PhD in relevant field.
• 2+ years ML/RL/robotics experience.
• Strong Python + PyTorch coding.
• Familiar with PPO, SAC, RL robotics.

Responsibilities

• Design, implement and iterate RL/IL training pipelines for humanoid tasks in simulation and real world.
• Create diverse task suites for manipulation, navigation, whole-body coordination in simulation.
• Manage training experiments: Hyperparameter tuning, Benchmarking, Logging and Failure analysis.
• Collaborate with multidisciplinary teams including: Motion and control engineers, Mechanical design team, Simulation engineers.
• Support sim-to-real transfer by adapting policies to real robot constraints and validating performance during deployment.

Skills

Python

PyTorch

Reinforcement learning

Machine learning

RL algorithms

Robotics concepts

Education

MS or PhD in Robotics/Automation/CS

Tools

Isaac Lab

Stable Baselines

Job description

Oversonic Robotics Srl is seeking a researcher to develop learning-based control strategies for humanoid robots. You will build training pipelines, design diverse task environments, and manage experiments from simulation to real-world validation.

The role requires strong Python and PyTorch skills, experience with RL algorithms, and a proven ability to translate learning into reliable robot behaviors while addressing sim-to-real challenges.