Robotics AI Engineer - Train Policies on Humanoid Robots

MENLO RESEARCH PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Menlo Research Pte. Ltd. in Singapore is seeking a Robotics AI Engineer to bridge learning and hardware on Asimov humanoid robots.

This role emphasizes getting results on real robots rather than simulations, with close collaboration across hardware, firmware, and infrastructure teams. You will design and train RL and imitation policies for locomotion, manipulation, and whole-body control, run hardware experiments, and build data pipelines to accelerate policy iteration.

Qualifications

• Strong foundations in reinforcement learning or imitation learning.
• Hands-on experience training policies on real robots.
• Experience working with Python and ML frameworks.
• Ability to debug and iterate on hardware-in-the-loop experiments.
• Comfort working directly with robots, not just simulations.

Responsibilities

• Design and train RL and imitation learning policies for locomotion, manipulation, or whole-body control.
• Run experiments on physical hardware and close the sim-to-real gap through systematic debugging and domain adaptation.
• Build and maintain simulation environments and data pipelines that support fast policy iteration.
• Instrument robot deployments and analyze failure modes to feed improvements back into training.
• Collaborate with hardware and firmware engineers to understand physical constraints and improve policy robustness.

Skills

Reinforcement learning

Imitation learning

Python

Robotics experience

Experimentation

Tools

JAX

PyTorch

MuJoCo

IsaacGym/IsaacLab

Job description

Menlo Research Pte. Ltd. in Singapore is seeking a Robotics AI Engineer to bridge learning and hardware on Asimov humanoid robots.

This role emphasizes getting results on real robots rather than simulations, with close collaboration across hardware, firmware, and infrastructure teams. You will design and train RL and imitation policies for locomotion, manipulation, and whole-body control, run hardware experiments, and build data pipelines to accelerate policy iteration.