Reinforcement learning Engineer

• Algorithm Development & Research
• Design and implement reinforcement learning algorithms (e.g., Q-learning, PPO, DDPG, SAC).
• Research and experiment with state-of-the-art RL methods, including hierarchical and multi-agent learning.
• Apply RL techniques to real-world problems such as robotics, recommendation systems, or dynamic resource optimization.
• Model Training & Evaluation
• Build simulation environments for RL training and testing (e.g., Gym, Isaac Gym, PettingZoo).
• Develop reward functions, state representations, and policy optimization strategies.
• Conduct hyperparameter tuning, ablation studies, and performance benchmarking.
• Productionization
• Collaborate with MLOps and engineering teams to deploy RL agents in production environments.
• Optimize models for scalability, latency, and reliability.
• Implement monitoring and feedback loops for continuous improvement of deployed agents.
• Collaboration & Documentation
• Work cross-functionally with research scientists, software engineers, and product managers.
• Document algorithms, experiments, and results for internal use and publication.
• Contribute to open-source projects or internal research papers where applicable.

Do you have experience in Machine learning?