• You will design and implement scalable APIs for agent orchestration and learner interaction • You will build data pipelines that feed agent evaluation and continuous improvement cycles • You will create event streaming infrastructure for real-time learner interaction analysis • You will ensure data quality and accessibility for training and evaluating learning agents • You will improve data infrastructure for cost and performance in close coordination with Data and ML teams • Design and implement rigorous evaluation frameworks to measure agent performance and improve cycles • Develop LLM evaluation processes and perform error analysis to identify systemic improvements for agentic learning systems • Support instrumentation that makes evaluation relevant (metrics, traces/logs, and analysis workflows) • Participate in on-call rotation and incident response for learning platform reliability • Contribute to runbooks, postmortems, and reliability improvements as we evolve our operating model