Senior Benchmark Engineer - Public Data Provider Evals

Firecrawl is seeking a Research Engineer to design and run head-to-head benchmarks of data providers, establishing ground truth, and shipping a reproducible weekly release. You’ll evaluate accuracy, coverage, freshness, speed, and cost while collaborating with marketing to publish public leaderboards.

You’ll own the test datasets, scoring methods, and the loop into Alexandria. This role requires 4+ years in ML, data engineering, or benchmark work and a track record of shipping tangible evals in