Raydar
Research Engineer
$250K–$290K
San Francisco, California · Full-time · Posted Oct 12, 2026
About the job
Designs and builds systems to measure the quality of machine-learning outputs, using evaluation findings to inform model and product decisions.
What you'll do
- Define quality measures and build reliable, scalable evaluation pipelines.
- Create and curate labeled reference data for comparing model outputs.
- Communicate evaluation results and connect them to model and product decisions.
What they ask for
- Proven experience building evaluations for LLM-based data extraction or data quality at scale.
- Experience creating scoring approaches and evaluation systems, and assembling human-labeled or verified reference data.
- Evaluation work that influenced model or product decisions, supported by work history.
- Strong Python skills and a solid grounding in statistics.
Pay
USD 250,000 to 290,000 per year (base salary)
Tools
Python
AI focus
Evaluates LLM-based data extraction or data quality and uses findings to guide model and product decisions.
Model-written summary · the original posting is authoritative