Research Engineer, Evals

ABOUT THE ROLE

Build evaluation systems for a web data extraction product that turns URLs into clean, structured data for AI applications. You will define how output quality is measured and connect evaluation results to model and product decisions.

WHAT YOU'LL DO

• Design rigorous metrics for extraction quality across diverse websites, formats, and edge cases.
• Build scalable evaluation pipelines and harnesses.
• Generate and curate trusted datasets for measuring extraction quality.
• Close the feedback loop between evaluation results and model or product decisions.
• Make evaluation results clear and actionable for the broader team.

WHAT WE'RE LOOKING FOR

• Typically 4 to 10+ years of relevant experience, including at least 2 years focused on evaluations.
• Experience building evaluation systems for LLM-based structured extraction from messy, real-world web pages or documents, including field-level accuracy measurement at scale.
• Strong Python skills and experience with machine learning, LLMs, data pipelines, evaluation frameworks, web scraping, NLP, and statistical analysis.
• Ability to design evaluation metrics and systems from the ground up, apply statistical rigor, and build gold-label or reference-extraction datasets.
• Experience combining research methodology with engineering, and using evaluation findings to inform real model or product decisions.

COMPENSATION & BENEFITS

Base salary: $250,000 to $290,000 USD annually. Visa sponsorship is available.

LOCATION

Hybrid, with the primary location in San Francisco, California. Toronto, Canada is also a work location. The role requires working on-site five days a week in San Francisco or Toronto.