IT Staffing Firm · Staffing · Recruitment
Hybrid RAG that matches candidates to roles in seconds.
A hybrid lexical + semantic retrieval system that ranks candidates against job requirements with cited evidence from the resume.
9×
faster shortlist generation per requisition
+38%
interview-to-offer conversion on shortlisted candidates
100%
shortlist decisions backed by cited resume evidence
Staffing · Recruitment
IT Staffing Firm
Client
IT Staffing Firm
Staffing · Recruitment
Headline metric
9×
faster shortlist generation per requisition
Deliverables
4
shipped to production
Stack
4+ tools
across the build
Challenge
An IT staffing firm's recruiters were shortlisting candidates by hand, taking 4–6 hours per requisition. Generic ATS keyword matching missed strong candidates and surfaced weak ones. Recruiters didn't trust pure-LLM matching — too many opaque false positives.
Approach
Built a hybrid RAG (BM25 + dense embeddings) that ranks candidates against job requirements and surfaces cited evidence from the resume for each match factor. Recruiters review the evidence, not the model's opinion. Continuous feedback loop tunes the ranker against actual hire outcomes.
Outcome
Shortlist generation 9× faster, interview-to-offer conversion up 38%, and 100% of decisions backed by cited resume evidence. Recruiters reported trusting the system after week two.
Shortlist generation 9× faster, interview-to-offer conversion up 38%, and 100% of decisions backed by cited resume evidence. The team owned this end-to-end.
IT Staffing Firm
Staffing · Recruitment
faster shortlist generation per requisition
interview-to-offer conversion on shortlisted candidates
shortlist decisions backed by cited resume evidence
What we shipped.
- Hybrid retrieval ranker
- Evidence-citation UI
- Feedback loop
- ATS integration
The tools we used.
More case studies
All case studies
EdTech · Series A
Mockinto
47%
An AI interviewer that actually adapts to the candidate.
A multi-turn interview agent that adjusts difficulty in real time, scores answers against a rubric, and gives structured feedback in under two seconds.
Read case
Legal · Litigation
Mid-size Law Firm
−68%
An agentic AI system that researches case law — and shows its work.
Automating multi-step legal research with bounded agents that cite, summarise, and flag for review.
Read caseLet's talk about your version of this.
30-minute discovery call. No NDA gatekeeping. We'll tell you straight whether we're a fit.
info@aiinfox.com