RAG & SearchSemantic searchRerankingHourly
Semantic Search Relevance for a Content Site
Wayfinder Data · Remote (US/EU)
$85 / hr
The outcome
Their search returns near-misses; they need embeddings + reranking so results actually match what readers meant.
The client
Wayfinder Data — Remote (US/EU). A rag & search build we delivered end to end.
The challenge
Upgrade a keyword search to hybrid semantic search over a large content library and tune relevance with a real query eval set.
What we built
- Add embeddings + hybrid retrieval to the existing search
- Tune relevance against a labeled query set
- Ship latency and quality benchmarks
The stack
Stack: embeddings, a vector store, and search-relevance evaluation.
Want something like this?
Tell us what you're building and we'll scope it — most projects start within a week.