Software Engineer, Agent Evaluation and Quality
Cursor · San Francisco · New York
CHECKED 7H AGO
Applied AIonsite
At a glance
Highlights
- Build measurement and eval infrastructure to make the core agent better over time.
- Design feedback loops from real usage to inform model and harness changes.
- Define quality for agent sessions with replay, judges, and regression alerts.
Ideal candidate
Truth-seeking, passionate builder who loves spirited debate and shipping code, with strong taste for agent behavior and drive to turn ambiguous quality questions into measurable improvements.
Requirements
- Built and operated evaluation or measurement systems such as AI evals, experimentation, ranking/relevance, or search quality
- Ability to turn ambiguous quality questions into concrete metrics, pipelines, and decisions
- Strong data acumen and ability to collaborate with data scientists and researchers
- Taste and strong opinions on model and agent behaviors
- Up-to-date on emerging research and industry trends
- Strong software engineering fundamentals and enjoys shipping production systems
- hiring process
- 2-3 short technicals, then onsite with a small project, idea discussions, and meeting the team.
Lab profile
About Cursor
Automates coding with AI-powered editor for professional programmers.
What they build
- Cursor AI code editor
- Cursor for Enterprise
Known for
- AI-assisted coding
- Applied ML research
- Developer tools
Key facts
- Founded in 2022
- Headquartered in San Francisco
- Backed by Thrive Capital and Andreessen Horowitz