← Back to michaeleakins.com

Case study

Making role search accurate with RAG

Candidates searching for roles got results that were only roughly aligned with what they searched for. I led the team that fixed it, and I built it hands-on alongside them.

Role
Engineering leader and hands-on builder
Platform
AWS Bedrock
Approach
Retrieval-augmented generation
internal documents chunked and indexed
400
gold standard searches with expected results
300
the index behind every retrieved passage
Doc · page · line

01 The problem

Close was not close enough

Candidates searching for roles got results that were only roughly aligned with what they searched for.

02 What I built

Retrieval grounded to the line

I led the team that built a retrieval-augmented generation pipeline on AWS Bedrock, and I built it hands-on alongside them. We split 400 internal documents into chunks and indexed every chunk by document, page and line. When a candidate searches, the LLM receives a prompt grounded in the exact passages that matter, and each passage traces back to its source.

  1. 01 Documents 400 internal documents
  2. 02 Chunks indexed by document, page and line
  3. 03 Retrieval the passages that match the search
  4. 04 LLM prompt grounded in those exact passages
  5. 05 Results close matches for the candidate

Test loop Every change ran against 300 gold standard searches.

03 How we proved it worked

A test set, not a gut check

I created a gold standard set of 300 searches, each with its expected results. Every change ran against that set, so we tested result quality reliably instead of judging it by eye.

04 The result

From roughly aligned to closely matched

Results went from roughly aligned with candidate searches to closely matching what candidates were looking for. The 300 gold standard searches let us confirm that on every change.

Building search or RAG that has to be right?

I am open to discussing engineering leadership opportunities.