Reinforcement Learning & Optimization Intern

The role involves reinforcement learning research and optimization projects for complex decision-making systems. Interns will develop, train, and evaluate RL models, design learning environments and reward functions, improve training efficiency, and contribute to large-scale AI optimization initiatives. Required skills include Python, PyTorch or JAX, PPO, Stable Baselines, TorchRL, and strong mathematical problem-solving capabilities. Candidates should have a strong interest in reinforcement learning, optimization, and AI research. Applications require a resume, portfolio or GitHub profile, and a short written response.