rank-eval

Builds ranking evaluation workflows including NDCG/MRR metrics, human relevance labeling, and offline evaluation harnesses. Useful for search relevance and recommender system testing.

Audits ranking quality by analyzing metric trends, failure modes, dataset coverage, and reranker performance.

Designs ranking pipelines with reranker selection, score fusion, and cross-encoder patterns. Useful for optimizing search or recommendation ranking with latency trade-offs.