About this role
Design, train, and deploy reinforcement learning (RL)-based systems for high-impact decision-making problems, including simulation, reward modeling, large-scale experience collection, and training policies on GPU clusters for production deployment.
Skills for this role
Reinforcement LearningPythonModern deep learning frameworksReinforcement learning librariesProbabilityOptimizationReward function designSimulation environmentsLarge-scale experience collectionTraining neural network policiesGPU clustersCommunication skillsMachine LearningRLHFMulti-agent reinforcement learningHierarchical reinforcement learningRoboticsControl systemsAutonomous drivingResearch publicationsOpen-source contributions