Develop reinforcement learning systems for autonomous agents by designing high-fidelity 2D/3D simulation environments, reward functions, and policy architectures. Implement and optimize algorithms such as PPO, SAC, and Offline RL for high-dimensional observations. Develop sim-to-real strategies using domain randomization and adaptation, collaborate with ML, annotation, and program management teams, and ensure reliable agent performance and environment parity.

Design and implement software architecture integrating machine learning models with real-time rendering systems. Evaluate customer requirements, determine build-versus-buy approaches, and route specialized needs to deep learning or reinforcement learning teams. Develop language-agnostic wrappers, APIs, and microservices while coordinating technical requirements among customers, leadership, and engineering. Translate product visions into modular, scalable, maintainable software components.