Robotics AI Engineer — Real-World Policy & Hardware Impact

Menlo; Palo Alto (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Menlo Research is seeking a Robotics AI Engineer to work at the intersection of learning and hardware, training policies that run on Asimov robots in the real world.

You will collaborate with the hardware, firmware, and infrastructure teams to close the loop between training and deployment, delivering results on physical robots rather than simulations.

You will iterate quickly, debug challenges on real hardware, and contribute to open-source robotics initiatives.

Qualifications

• Strong foundations in reinforcement learning or imitation learning with hands-on real-system policy training.
• Comfort working directly with robots, not only simulators.
• Proficiency in Python and RL frameworks (JAX, PyTorch, MuJoCo, or similar).
• An empirical, debugging-first mindset focused on hardware viability.
• Ability to move fast and context-switch between research problems and engineering tasks.

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

RL/IL fundamentals

Robot policy deployment

Python + RL frameworks

Empirical debugging

Fast context-switch

Humanoid/legged robotics (nice-to-have

Domain randomization (nice-to-have

Open-source robotics contributions

Control theory / dynamics (nice-to-ha

Tools

JAX

PyTorch

IsaacGym/IsaacLab

MuJoCo

Job description

Menlo Research is seeking a Robotics AI Engineer to work at the intersection of learning and hardware, training policies that run on Asimov robots in the real world.

You will collaborate with the hardware, firmware, and infrastructure teams to close the loop between training and deployment, delivering results on physical robots rather than simulations.

You will iterate quickly, debug challenges on real hardware, and contribute to open-source robotics initiatives.