HR Tech RAG Architecture Knowledge Graph Multi-LLM

Hunel: AI-Native
Recruitment Intelligence

Building a production RAG system that transforms how recruiters discover and match candidates — with multi-LLM orchestration, hybrid semantic search, and agentic workflows.

Multi
Data Sources
90%+
Match Accuracy
<1s
Search Latency
Major
Time Savings

Production AI Stack

Knowledge graph for skill/role relationships
RAG with hybrid retrieval (dense + sparse + graph)
Multi-LLM orchestration with intelligent routing
Graph neural network-inspired matching
Multi-vector embeddings per entity
GDPR-compliant EU-hosted inference
In Production
All metrics are approximate ranges. Technical details and proprietary methodologies have been generalized.
The AI Problem

Keyword Matching Is Fundamentally Broken

Traditional recruitment technology relies on keyword matching — a fundamentally broken approach. "Python Developer" doesn't match "Software Engineer (Python)". Scanned CVs are invisible. Skill relationships are ignored.

Hunel needed an AI system that understands recruitment the way humans do — but at machine scale and speed. Not another chatbot wrapper. A production-grade RAG system that could:

  • Ingest and index data from multiple job boards and employment services
  • Process any CV format — text, scanned, creative/infographic
  • Understand semantic relationships between skills, roles, and career trajectories
  • Explain why a candidate matches, not just return a score

Keyword mismatch

Qualified candidates missed by exact matching

30% CVs invisible

Scanned documents can't be searched

No skill relationships

"React" doesn't surface "Frontend" experts

Black box scoring

No explanation for why candidates match

The Solution

What We Delivered

90%+
Match Accuracy
vs recruiter decisions
Major
Screening Reduction
time saved per role
Fast
CV Processing
including OCR
3x+
Throughput
qualified candidates

Hybrid Semantic Search

Dense + sparse + graph retrieval with cross-encoder reranking. Not just vectors — real understanding of skill relationships.

Explainable AI Matching

Every match comes with human-readable reasoning: strengths, gaps, deal-breakers, and recommended pitch angles.

Agentic Workflows

Autonomous agents with tool-calling that search, score, enrich, and draft personalized outreach — with human-in-the-loop approval.

Multi-Modal CV Processing

Text, scanned, creative/infographic — all processed with OCR, Vision AI, and structured extraction. No CV left unsearchable.

Technical Deep Dive

The RAG Architecture

A production-grade retrieval system that goes far beyond basic vector search

Core Capabilities

Intelligent Search

Beyond keyword matching — understanding intent, context, and semantic relationships

Precision Matching

Multi-stage refinement to surface the most relevant candidates with high confidence

Explainable Results

Clear reasoning for every match — strengths, gaps, and recommended approaches

Multi-Vector Embeddings

Not one embedding per CV — multiple vectors for skills, experience, trajectory, and ideal job. Match on specific experience, not just overall profile.

Multi-LLM Orchestration

Intelligent routing by task complexity, latency, and privacy requirements. Reasoning LLM for complex matching, speed LLM for autocomplete, privacy LLM for sensitive data.

Knowledge Graph

Graph neural network approach: skills, roles, companies, and trajectories as nodes. Relationships encode "leads to", "requires", "similar to". Traverse the graph to expand queries and infer implicit matches.

Vision AI Processing

OCR with language detection. Image preprocessing. Creative CV extraction. Portfolio screenshot analysis. No document type left unsearchable.

Structured Extraction

LLM-powered parsing to JSON schema. Experience, skills, achievements, seniority level — all inferred and structured from raw text.

GDPR-Compliant Inference

EU-hosted LLM options for sensitive PII. Data residency controls. Automatic routing of personal data to compliant endpoints.

Graph Intelligence

Knowledge Graph

Why vectors alone aren't enough — and how graph relationships enable true semantic understanding

The Problem with Pure Vector Search

Vector similarity finds "Python Developer" ≈ "Software Engineer" — but it doesn't understand that Python → Django → Web Backend → API Design is a skill progression. It doesn't know that someone who did Django for 5 years probably knows REST APIs, even if they never listed it. That's where the graph comes in.

Vector-Only Approach

"React Developer" and "Frontend Engineer" are similar vectors, but you miss that React → TypeScript → Testing Library is a common skill cluster that implies deeper frontend expertise.

Graph-Enhanced Approach

Traverse from "React" node to connected skills. Weight by co-occurrence frequency. Expand the search to include implied competencies. Score based on graph centrality.

Graph Node Types & Relationships

S
Skills
Python, React, AWS...
R
Roles
Backend Dev, Tech Lead...
C
Companies
Type, size, industry...
T
Trajectories
Career paths, progressions...
// Graph query — Expand skill query with graph traversal
MATCH
(skill:Skill {name: "Python"})
-[:OFTEN_USED_WITH|LEADS_TO|REQUIRES*1..2]->
(related:Skill)
WHERE
related.category IN ["backend", "data", "devops"]
RETURN
related.name, count(*) as weight
ORDER BY
weight DESC

Graph Neural Network-Inspired Matching

Message Passing

Skills "propagate" relevance to neighbors. A strong Python signal boosts Django, FastAPI, Flask nodes in the candidate's profile.

Graph Centrality

Candidates with skills at "hub" positions (high connectivity) are more versatile. PageRank-style scoring identifies T-shaped profiles.

Path Analysis

Career trajectory = path through role nodes. Predict next likely role. Identify unconventional but successful transitions.

Technology

A Typical Production Stack

Modern, scalable architecture using industry-standard tools

AI & Machine Learning

LLM Orchestration Graph Database Vector Store Semantic Reranking Multilingual Embeddings

Backend

Server Runtime Type-Safe Language Web Framework Async Workers Message Queue

Data Layer

Relational Database In-Memory Cache Object Storage Search Engine

Infrastructure

Containerization Multi-Service Architecture API + Worker Separation
The Value Proposition

Why AI for Recruitment

How modern AI transforms the candidate matching experience

Speed at Scale

Process thousands of candidates in the time it takes to review a handful manually. AI handles the volume while recruiters focus on relationships.

Consistent Quality

Every candidate evaluated against the same criteria. No fatigue bias, no rushed decisions during high-volume periods. Reliable assessments every time.

Deeper Insights

Go beyond keyword matching to understand skills, potential, and career trajectory. Surface candidates that traditional searches would miss.

Key Innovations

What Made This Different

1

Context → Map → Match Pipeline

Job titles are subjective garbage. "Tech Lead" means different things everywhere. So we extract context first (responsibilities, team size, tech), map to a normalized taxonomy (ESCO), then match. Never skip to similarity without understanding.

2

Multi-Vector CV Representation

Instead of one embedding per candidate, we generate multiple vectors capturing different aspects: skills, experience, trajectory, ideal job. "Show me candidates who HAVE DONE fintech" vs "know fintech".

3

Hybrid Retrieval with Reranking

Combining dense (semantic), sparse (keyword), and graph (relational) search with cross-encoder reranking. Vectors alone miss exact matches. Keywords alone miss semantics. We use both.

4

Explainable AI Matching

Every match score comes with human-readable reasoning — strengths, gaps, deal-breakers, and recommended pitch angles. Recruiters can trust and verify.

Key Insight

What I Learned

" The hardest part of recruitment AI isn't the LLM — it's understanding that job titles are meaningless without context. A 'Senior Developer' at a startup has completely different experience than one at an enterprise. The breakthrough: context first, then map to taxonomy, then match. You can't skip straight to vector similarity. The AI is a small part of the work. The rest is understanding the domain well enough to know what actually matters. "

Building an AI System?

Whether it's RAG, multi-LLM orchestration, agentic workflows, or semantic search — I've shipped production systems that handle the hard parts. Let's talk about your project.

Let's Talk About Your AI Project

All metrics are approximate ranges. Technical details and proprietary methodologies have been generalized.

Available now

Let's Build Something That Ships

Free 30-minute strategy call. No pitch deck. No sales pressure. Just an honest conversation about your project.

Faster
50%
Less cost
100%
Satisfaction
No commitment
24h response
Free discovery call

Trusted by startups, scale-ups, and enterprises across France and internationally.