Algorithm Engineer, Reinforcement Learning

What you'll do

• Develop and train conditioned policies that simulate realistic driving behaviors for testing the autonomous-driving stack.
• Research and implement safety-constrained RL algorithms, reward functions, and evaluation metrics.
• Improve scalable training environments and neural architectures, and integrate models with Simulation and Planning teams.

What they ask for

• Proven experience training and deploying deep RL algorithms such as PPO or SAC for complex real-world robotic or autonomous systems.
• Expertise in Python and PyTorch, with a strong understanding of deep-learning architectures and optimization.
• MS or PhD in Computer Science, Robotics, or a related quantitative field.
• Ability to diagnose RL training challenges, including variance management and distribution shift.

Nice to have

• Experience with constrained optimization or safety-critical learning frameworks.
• MARL experience, familiarity with vehicle dynamics and behavior planning, or experience with long-haul highway environments.

Tools

PPO, SAC, Python, PyTorch

AI focus

Develops deep and multi-agent reinforcement-learning policies for autonomous trucks, including safety-constrained learning, simulated driving behaviors, and planning.