The role involves leading a team of research engineers focused on evaluation infrastructure within an artificial intelligence research laboratory. The team is responsible for curating and building benchmarks for advanced models across various modalities including text, vision, and audio. The manager will define strategic visions for evaluation infrastructure while ensuring the delivery of scalable benchmarks and reinforcement learning environments. This position requires balancing hands-on technical contributions with people management and cross-functional collaboration. The individual will guide the team through complex machine learning challenges while maintaining high engineering standards and reliability.