Robotics AI Engineer

Auxo Talent; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Auxo Talent is seeking a Robotics AI Engineer to work at the intersection of learning and hardware on a humanoid platform. You will train and deploy policies that run on our client’s robots in the real world, iterating quickly when things break and closing the loop with hardware, firmware, and infrastructure teams.

You will design RL/IL policies for locomotion, manipulation, or whole-body control, run experiments on physical robots, and build data pipelines to support rapid iteration.

Qualifications

• Strong foundations in reinforcement learning or imitation learning with hands-on experience.
• Comfort working directly with robots, not just simulators.
• Proficiency in Python and familiarity with standard RL/ML frameworks.

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.
• Build and maintain simulation environments and data pipelines to 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

Robotics

Python programming

Experimentation

Tools

PyTorch

TensorFlow

ROS

Gym

Job description

About Our Client

Our client is an applied robotics R&D company building a next-generation humanoid robot platform and the full software stack that powers it. They work across the full stack: hardware architecture, locomotion, autonomy, simulation, and infrastructure. The team moves fast, ships to real robots, and believes the best ideas should be built and tested in the physical world, not just in a lab.

The Role

As a Robotics AI Engineer, you'll work at the intersection of learning and hardware, training and deploying policies that run on our client's humanoid platform in the real world. This is not a research role in the traditional sense. You'll be expected to get results on physical robots, not just in simulation, and to iterate quickly when things break. You'll work closely with the hardware, firmware, and infrastructure teams to close the loop between training and deployment.

What You'll Do

• 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 directly with hardware and firmware engineers to understand physical constraints and improve policy robustness

What Our Client Is Looking For

• Strong foundations in reinforcement learning or imitation learning, with hands-on experience training policies that run on real systems
• Comfort working directly with robots, not just simulators
• Proficiency in Python and familiarity with standard RL/ML frameworks
• An empirical, debugging-first mindset
• Ability to move fast and context-switch between research problems and engineering tasks

Nice to Have

• Prior work on humanoid or legged robot platforms
• Experience with sim-to-real transfer techniques (domain randomization, system identification, noise injection)
• Contributions to open-source robotics projects
• Background in control theory, trajectory optimization, or dynamics