Research Engineer (Evaluation Systems)

About the role

Firecrawl is looking for a Research Engineer to design and operate evaluation systems that verify the quality of its web‑to‑data conversion platform. You will define what "good output" means across millions of web pages and build the infrastructure that measures it at scale.

Key responsibilities

• Design metrics that capture output quality for diverse sites, formats, and edge cases.
• Build robust pipelines and harnesses to evaluate performance rigorously and at scale.
• Generate, curate, and maintain datasets that ensure trustworthy evaluation.
• Own the feedback loop from evaluation results to model and product decisions.
• Translate evaluation findings into actionable insights for the whole team.

Required profile

• 4+ years of experience in machine learning, research engineering, or data‑intensive backend development.
• Hands‑on experience creating and running real evaluation frameworks.
• Strong analytical mindset with a passion for defining and measuring quality.
• Legally authorized to work in the United States (no visa sponsorship available).

Required skills

What we offer

• Competitive salary range $210,000–$275,000 per year.
• Equity package disclosed during the interview process.
• Hybrid work model in San Francisco with on‑site collaboration.
• Opportunity to shape core evaluation infrastructure for a fast‑growing AI company.