Senior AI Engineer (Closed-loop Simulation & RL)
Core
Designing and developing closed-loop evaluation frameworks to assess and continuously improve autonomous driving foundation models and decision-making policies using simulation and reinforcement learning.
Role type
Senior AI Engineer (Autonomous Driving, Closed-loop Simulation & RL)
Builds
Autonomous driving decision models, closed-loop evaluation systems, and safety-critical scenario pipelines.
Domain
Autonomous driving, Reinforcement Learning, Simulation, Robotics
Deliverable
production ML models
Required skills
Reinforcement Learning, Imitation Learning, Trajectory Planning, Simulation, Python, PyTorch, Reward Modeling, Policy Distillation, Offline RL, Sequential Decision Making, Failure Analysis, Large-scale Experiment Automation
Preferred skills
Autonomous Driving Simulators (Waymax, CARLA, nuPlan, NavSim), Model-based RL, Safe RL, Preference Modeling, Multi-agent Simulation, Neural Rendering (3DGS, NeRF), Synthetic Data Generation, Simulation-to-real Correlation Analysis, Distributed Rollout Infrastructure, VLA/World Model Post-training
Responsibilities
Design and develop closed-loop evaluation frameworks for Driving VLA/World Model/Planning models; Build log replay, scenario-based simulation, regression test, and safety-critical case mining pipelines; Improve driving policies using RL, offline RL, reward modeling, policy distillation, and post-training; Design and operate simulation rollout, reward function, evaluation metric, and failure analysis pipelines; Define autonomous driving quality metrics (safety, comfort, progress, rule compliance) and build model evaluation systems; Develop model improvement loops using counterfactual simulation, synthetic scenarios, and real-world driving logs; Collaborate with VLM/VLA, Data, and ML Platform organizations to integrate closed-loop learning/evaluation systems.
Seniority
Senior, hands-on IC
