Engineering Manager Evals
Posted
You will set the evaluation roadmap and lead engineers and researchers building datasets and tools for evaluations. You will guide CursorBench, define online quality signals, turn regressions into guardrails, and integrate evaluations into launches, deployments, and model-training decisions.
Responsibilities
- Set the end-to-end evaluation roadmap
- Lead engineers and researchers building evaluation datasets and tools
- Guide the next generation of CursorBench
- Define online quality signals and guardrails
- Integrate evaluations into launches, deployments, and model training
Requirements
- Engineering management
- Evaluation system
- Evaluation dataset
- AI evaluation
- Experimentation
- Ranking
- Relevance
- Search quality
- Reliability instrumentation
- Data science
- Research