ML/RL Engineer, Behavior Planning

About this role

Bot Auto seeks an ML/RL Engineer to develop behavior planning systems for autonomous semi-trucks. You'll design safety-constrained reinforcement learning policies, build scalable multi-agent training pipelines, and bridge simulation with real-world autonomous driving deployment.

What you'll do

• Develop and train diverse, conditioned policies for realistic driving behavior simulation and stress-testing
• Research and implement safety-constrained RL algorithms with safety as primary learning constraints
• Design reward functions and evaluation metrics balancing safety, progress, and comfort
• Optimize large-scale, high-throughput training environments for multi-agent scenarios
• Advance neural architectures for spatial reasoning, long-horizon planning, and agent interaction modeling
• Collaborate with Simulation and Planning teams to integrate research models into production systems

What they're looking for

• Deep Reinforcement Learning (PPO, SAC, and similar algorithms)
• Python and PyTorch
• Multi-Agent Reinforcement Learning (MARL)
• Safety-critical system design
• Neural network architecture design
• Reward engineering and objective design
• Distributed training systems optimization
• Autonomous driving domain knowledge (preferred)

Benefits

• Competitive salary based on experience
• Performance bonuses and equity opportunities
• Comprehensive health insurance
• Paid time off
• Work on cutting-edge autonomous trucking technology