Firecrawl is seeking a Research Engineer - Benchmarks to design and run independent, public benchmarks of data providers. You will own datasets, ground truth, scoring, harness, and weekly releases, ensuring reproducibility and defensibility.
You'll ship evaluation methods, compare providers, and publish leaderboards that inform Alexandria's provider calls. This requires shipping benchmarks and maintaining test data in a fast, rigorous, and transparent manner.
#J-18808-LjbffrLead Public Benchmarks Engineer — Data Providers (Hybrid) in san francisco at Unknown Company
This position is listed as full time and onsite.