Reinforcement Learning Engineer (Autonomous Driving)

The role

This person will develop reinforcement learning methods to improve the driving performance of end-to-end driving models. They will lead everything from designing promising ideas to large-scale training, rigorous evaluation, and driving model integration.

What you will do

• Design VLA policy and simulator observation/action interfaces and develop closed-loop RL post-training using policy optimization techniques like GRPO and PPO.
• Develop self-play training structures where ego and traffic agents interact with the trained policy and past checkpoints in vector or occupancy-based driving simulators.
• Co-develop action selection based on expected return and safety constraints by rolling out candidate actions and trajectories in multiple future scenarios.
• Verify policy safety and generalization using closed-loop benchmarks and analyze reward hacking and simulator bias.

Required qualifications

• 3 or more years of experience in Machine Learning, Reinforcement Learning, or Robotics or equivalent research/development capabilities.
• Experience implementing policy learning algorithms and performing training and evaluation with Python and PyTorch.
• Understanding of policy optimization, reward design, and credit assignment and ability to design RL experiments.
• Experience training policies in simulation or multi-agent environments and verifying improvements against baselines.
• English communication skills to discuss and collaborate on technical issues with overseas offices.

Nice to have

• Experience developing training structures using self-play, multi-agent RL, or policy population.
• Experience applying RL post-training such as GRPO or PPO to VLA or generative policy.
• Experience training policies in vector or occupancy-based driving simulators or developing world model-based rollout planning.
• Experience with large-scale parallel rollout, distributed training, or sim-to-real verification.

Benefits

• Preferential treatment for persons entitled to national meritorious service and employment protection under relevant laws.
• Preferential treatment for persons with disability registration under the Act on Employment Promotion and Vocational Rehabilitation of Persons with Disabilities.

Before you apply

• Do not include prohibited information such as resident registration number, family relations, marital status, annual salary, photo, or physical conditions in the application.
• Employment may be canceled if false information is found in the application.
• Reference checks may be conducted after the interview process with the candidate's consent.
• A 3-month probation period may apply.

About the company

42dot's autonomous driving VLA team develops technology that enables vehicles to understand complex road situations and connect judgments to driving actions through Vision-Language-Action (VLA) models.