6 months ago
Responsibilities
- Design and build AI evaluation systems with curated datasets, offline replay, scorers or judges, regression alerts, and dashboards.
- Develop feedback loops by collecting, cleaning, and interpreting user signals to guide model and harness changes.
- Build analysis tooling for debugging agent behavior, investigating failure modes, clustering themes, and surfacing actionable insights.
- Define and operationalize agent quality states, alerting, reliability guardrails, and triage primitives.
- Partner with research, product, data, and infrastructure teams to improve model quality, cost, and agent behavior.
Requirements
- Experience building and operating evaluation or measurement systems such as AI evaluations, experimentation, ranking or relevance systems, or search-quality systems.
- Ability to turn ambiguous quality questions into concrete metrics, pipelines, and decisions.
- Strong data acumen and ability to collaborate with data scientists and researchers.
- Strong software engineering fundamentals and enthusiasm for shipping production systems.
- Interest in model and agent behavior and awareness of emerging research and industry trends.
Categories
About Cursor
Cursor is an AI-powered code editor and coding assistant from Anysphere, built for professional software engineers and enterprise teams. It combines a VS Code–style editor with integrated AI chat, code generation, and repo-aware refactoring, and is sold via individual, team, and enterprise subscriptions. The company also targets sectors like healthcare and state and local education with field engineers who support evaluations and proofs of concept.