Machine Learning Engineer – RL

Responsibilities: Develop and deploy production-ready reinforcement learning systems for complex sequential decision-making challenges. This includes designing reward functions, building scalable training pipelines, and maintaining simulation environments.

Requirements: Requires a Master's or PhD in a technical field and over 6 years of experience in RL research and engineering. Candidates must be proficient in Python and deep learning frameworks with a strong grasp of optimization and probability.

Key skills: Reinforcement Learning, Python, Deep Learning Frameworks, RLHF, DPO, Policy Optimization, Reward Modeling, Distributed Training, Simulation Environments, Offline RL, Imitation Learning, Actor-Critic, GPU Clusters, Probability, Optimization Methods, Software Engineering

Keywords: Machine Learning, Reinforcement Learning, RLHF, DPO, Python, Deep Learning, Policy Gradient, Actor-Critic, Offline RL, Imitation Learning, Distributed Computing, GPU Clusters, Simulation Environments, Reward Shaping, Large Language Models, Multi-agent RL, Hierarchical RL, Robotics, Autonomous Systems, Control Environments, AI Safety, Model Optimization, Scalable Infrastructure, Experience Replay, Robustness Testing, Adversarial Scenarios, Out-of-distribution Assessment, Neural Networks, Artificial Intelligence, Software Engineering