Lead Robotics Learning Engineer, Heavy Equipment Autonomy

AIM; Seattle (WA); On-site; USD 180,000 - 250,000; Full time

Job summary

AIM is hiring a Staff-level or senior Robotics Learning Engineer to lead data-driven autonomy for heavy equipment. You will shape technical direction, manage milestones, and hands-on implement learned policies on real robots and in simulation.

Key tasks include building data/training loops, evaluating RL/BC approaches, and mentoring teams across robotics, controls, and software. You will balance data quality with deployment constraints and drive reliable machine behavior on hardware.

Qualifications

• Demonstrated ownership at Staff level or above of substantial robotics or robot-learning efforts.
• Experience implementing, training, deploying, and evaluating learned policies on robots or vehicles.
• Hands-on contributions to production software, learning experiments, and hardware debugging.
• Experience mentoring engineers and improving technical decisions via design/code reviews.
• Strong understanding of ML, optimization, and sequential decision-making.

Responsibilities

• Lead technical direction and architecture decisions across data, simulation, training, policy inference, and evaluation.
• Develop and deploy learned autonomy policies for heavy equipment in real deployments.
• Build reproducible data, training, and evaluation workflows; analyze experiments and failures.
• Collaborate with robotics, controls, perception, software, and field teams; own key milestones.
• Write maintainable software; diagnose failures across system boundaries; contribute code.

Skills

Python

Machine learning

Reinforcement learning

Imitation learning

Policy deployment

Code reviews

Mentoring

Software design

Education

Robotics or CS degree

Tools

C++

PyTorch

JAX

Job description

AIM is hiring a Staff-level or senior Robotics Learning Engineer to lead data-driven autonomy for heavy equipment. You will shape technical direction, manage milestones, and hands-on implement learned policies on real robots and in simulation.

Key tasks include building data/training loops, evaluating RL/BC approaches, and mentoring teams across robotics, controls, and software. You will balance data quality with deployment constraints and drive reliable machine behavior on hardware.