Research Scientist (Remote/US/LATAM)

📋 Description Own how frontier model capability is measured. Design benchmarks that prove evaluation quality. Build evaluation packages across reasoning, coding, agents, multi-modal. Ground methods in expert-verified truth; validate across models; QC. Turn public benchmarks into original evaluation designs. Own questions of validity, headroom, discrimination, contamination. 🎯 Requirements Research background in ML evaluation or benchmarking. Deep LLM benchmarking expertise; strong in code-model eval. Fluency with frontier-model metrics: rubrics, headroom, contamination. Proven ability to hold a team or expert pool to a rigorous standard. Fluent English; Spanish a nice-to-have.