RESEARCH SCIENTIST - AGENTIC RL - REMOTE

About this role

JOB RESPONSIBILITIES Reward Design & Long-Term Decision Making: Develop effective reward mechanisms and solve long-term credit assignment challenges by connecting an agent’s short-term decisions with delayed outcomes, such as customer satisfaction, product returns, and user retention. User Modeling & Adaptive Agent Behavior: Design systems that can understand changing user preferences and behaviors, manage uncertainty, and determine the appropriate response, including asking questions, making r…