Senior Reinforcement Learning Engineer

What you'll do

• Build data-driven planning and control systems, improve simulation to address the sim2real gap, and establish real-data collection and curation pipelines.
• Design experiments and tools to evaluate and improve learned components; explore adaptive and online reinforcement learning in deployed systems.
• Integrate learned components into the software stack and mentor junior team members, interns, and students.

What they ask for

• 2–5 years of industry experience developing reinforcement learning for control and/or planning and deploying it on real robots with a customer.
• Experience with GPU-accelerated simulation environments.
• Strong Python skills and experience with PyTorch or similar libraries.
• Proficiency in C++; comfortable debugging real-world system behavior and willing to travel as required by business projects.

Nice to have

• Experience with hydraulic machinery, supervised or imitation learning, reinforcement-learning research, or large-scale robotics deployment.
• Familiarity with ROS or similar frameworks, ML data curation, staged deployments, mentoring, or AI coding tools.

Tools

Python, PyTorch, C++, IsaacSim/IsaacLab, CARLA, MuJoCo, ROS

AI focus

Develop data-driven and reinforcement-learning systems for autonomous excavation, including adaptive and online learning; improve simulation-to-reality transfer and train policies using curated real-world data.