AI Evaluation Science Engineer

This role involves independently managing end-to-end evaluations of advanced AI models and systems, from defining initial research questions through final executive recommendations. You'll work at the intersection of research and product by converting ambiguous business and customer needs into testable hypotheses, creating or selecting appropriate benchmarks, building evaluation infrastructure, and analyzing results with statistical rigor. The position requires strong scientific judgment combined with practical engineering skills—you'll write production-quality code, manage complex datasets, develop automated evaluation methods, and establish reproducible evaluation protocols. You'll collaborate across science, engineering, product, and operations teams while also contributing novel research publishable at top-tier conferences. This role suits experienced machine learning professionals who enjoy both independent technical work and stakeholder communication, with a passion for ensuring AI systems are evaluated thoroughly before reaching customers.