RAG & SearchRAGRerankingHourly
Prompt & Retrieval Tuning for a RAG App
Lucid Systems · Remote (Global)
$95 / hr
The outcome
Their RAG app works 70% of the time — they need someone to close the gap with better chunking, reranking, and prompts.
The client
Lucid Systems — Remote (Global). A rag & search build we delivered end to end.
The challenge
Audit an existing RAG pipeline and lift answer quality: fix chunking, add reranking, tighten prompts, and prove the gain with before/after evals.
What we built
- Diagnose retrieval failures with an eval-driven approach
- Improve chunking, add a reranker, and tune the answer prompt
- Report measurable quality gains against a fixed test set
The stack
Stack: RAG internals, rerankers, and prompt engineering with evals.
Want something like this?
Tell us what you're building and we'll scope it — most projects start within a week.