Engineering Manager, Evals

Responsibilities

• ▹Set the eval roadmap end-to-end: what to measure, why it matters, how signals turn into shipping and training decisions
• ▹Lead and grow a high-impact team of engineers and researchers building eval datasets and tools
• ▹Guide the next generation of CursorBench to keep reflecting real developer workflows and expand it with new evals
• ▹Define crisp online quality signals and turn regressions into robust guardrails
• ▹Integrate evals into decision-making cadence for launches, deploys, and model training loops

Requirements

• ▹Experience leading engineering teams shipping production systems, with strong people leadership and coaching skills
• ▹Ability to align research, product, data, and infrastructure into durable metrics, processes, and rituals
• ▹Good taste and strong opinions on model and agent behaviors, staying current with research trends
• ▹Strong data acumen, effective collaboration with data scientists and researchers
• ▹Experience building and operating evaluation or measurement systems (AI evals, experimentation platforms, ranking/relevance, search quality, reliability instrumentation)

Soft skills

About the company

Cursor's mission is to automate coding. The company is building the best tool for professional programmers through a combination of inventive research, design, and engineering. The organization is flat, with a small, talent-dense team.