Robotics Learning Engineer – Autonomous Heavy Equipment

AIM; Redmond; On-site; AUD 170,000 - 260,000; Full time

Job summary

AIM is seeking a Staff-level or higher Robotics Learning Engineer to lead the technical development of data-driven autonomy skills for heavy equipment. You will drive demonstrations, simulation, and real-world deployment, while shaping the technical roadmap and mentoring engineers.

The role demands hands-on coding, experimentation, and a strong background in reinforcement and imitation learning, with a track record of deploying policies on physical robots or vehicles.

Qualifications

• Experience leading robot-learning projects from problem to deployment.
• Depth in RL, imitation learning, or behavior cloning is required.
• Hands-on contributions to production software and hardware debugging.
• Mentorship and code review experience.
• Strong ML, optimization, and sequential decision-making insight.
• Proficiency in Python with PyTorch or JAX.

Responsibilities

• Lead the technical effort; define architecture across data, simulation, training, and controls.
• Develop and evaluate a POC to establish feasibility and baseline performance.
• Coordinate cross-team execution and mentor engineers.
• Build data pipelines: demonstrations, trajectories, interventions, and failure cases.
• Address deployment constraints: sensor noise, latency, and real-time performance.
• Validate changes through simulation and hardware trials with safety engineers.

Skills

Robot learning

Python

PyTorch

JAX

Reinforcement learning

Imitation learning

System integration

Mentorship

Code reviews

Education

Robotics/CS/EE/ME degree

Tools

PyTorch

JAX

Python

Job description

AIM is seeking a Staff-level or higher Robotics Learning Engineer to lead the technical development of data-driven autonomy skills for heavy equipment. You will drive demonstrations, simulation, and real-world deployment, while shaping the technical roadmap and mentoring engineers.

The role demands hands-on coding, experimentation, and a strong background in reinforcement and imitation learning, with a track record of deploying policies on physical robots or vehicles.