Physical AI Trainer - RoboGym (human)

Neura Robotics; Aachen; On-site; EUR 55,000 - 75,000; Full time

Job summary

Neura Robotics is seeking a hands-on trainer for NeuraGym users in Aachen, Germany. You will design training curricula, scope task feasibility, and plan demonstration and data-collection sessions for robot skill acquisition.

You will onboard users to the full NeuraGym pipeline—teleoperation, annotation, training, simulation, deployment, and validation—while collaborating with robotics engineers to ensure safe, reliable behaviors.

Qualifications

• Master’s degree in Computer Science, Robotics, Electrical Engineering, or related field.
• 3+ years of hands-on experience in robot learning or physical AI training.
• Solid Python skills (C++ a plus); practical experience with PyTorch or TensorFlow.
• Comfortable working directly with real robot hardware, teleoperation setups, and associated middleware.
• Cloud experience (AWS, Azure, or GCP) and experience with robotic simulation tools (IsaacSim, MuJoCo, etc.) is a plus.
• Strong instructional and problem-solving abilities; able to manage multiple training projects in parallel.
• Clear communicator who can translate between researchers, engineers, and end-users, with good command of English and German (B2–C1 level).

Responsibilities

• Act as hands-on trainer for NeuraGym users; design training curricula, scope task feasibility, and plan demonstration and data-collection sessions for robot skill acquisition.
• Onboard users to the full NeuraGym pipeline: teleoperation, annotation, training, simulation, deployment, and validation.
• Collaborate closely with robotics engineers during data capture and live demonstrations to ensure desired behaviors and safety standards are achieved.
• Guide users through model training and refinement: review training scripts, identify data quality issues, help reproduce and resolve learning failures; step in hands-on when a blocker persists.
• Serve as a key interface between trainees/users and the cloud and AI teams, facilitating collaboration and support where needed.
• Feed lessons learned from training sessions back into both the NeuraGym product roadmap and the Neura core AI roadmap.

Skills

Python

C++ (a plus)

Instructional abilities

Communication (EN/DE)

Education

Master’s degree (CS/Robotics/EE)

Tools

PyTorch

TensorFlow

AWS/Azure/GCP

MuJoCo

IsaacSim

Job description

Your mission & challenges

• Act as hands‑on trainer for NeuraGym users: design training curricula, scope task feasibility, and plan demonstration/data-collection sessions for robot skill acquisition

• Onboard users to the full NeuraGym pipeline: teleoperation, annotation, training, simulation, deployment, and validation

• Collaborate closely with robotics engineers during data capture and live demonstrations to ensure desired behaviors and safety standards are achieved

• Guide users through model training and refinement: review training scripts, identify data quality issues, help reproduce and resolve learning failures; step in hands‑on when a blocker persists

• Serve as a key interface between trainees/users and the cloud and AI teams, facilitating collaboration and support where needed

• Feed lessons learned from training sessions back into both the NeuraGym product roadmap and the Neura core AI roadmap

What we can look forward to

• Master’s degree in Computer Science, Robotics, Electrical Engineering, or related field

• 3+ years of hands‑on experience in robot learning or physical AI training

• Solid Python skills (C++ a plus); practical experience with PyTorch or TensorFlow

• Comfortable working directly with real robot hardware, teleoperation setups, and associated middleware

• Cloud experience (AWS, Azure, or GCP) and experience with robotic simulation tools (IsaacSim, MuJoCo, etc.) is a plus

• Strong instructional and problem‑solving abilities; able to manage multiple training projects in parallel

• Clear communicator who can translate between researchers, engineers, and end‑users, with good command of English and German (B2–C1 level)