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.
Production AI Stack
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
What We Delivered
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.
The RAG Architecture
A production-grade retrieval system that goes far beyond basic vector search
Core Capabilities
Beyond keyword matching — understanding intent, context, and semantic relationships
Multi-stage refinement to surface the most relevant candidates with high confidence
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.
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.
"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.
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
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.
A Typical Production Stack
Modern, scalable architecture using industry-standard tools
AI & Machine Learning
Backend
Data Layer
Infrastructure
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.
What Made This Different
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.
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".
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.
Explainable AI Matching
Every match score comes with human-readable reasoning — strengths, gaps, deal-breakers, and recommended pitch angles. Recruiters can trust and verify.
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 ProjectAll metrics are approximate ranges. Technical details and proprietary methodologies have been generalized.
Let's Build Something That Ships
Free 30-minute strategy call. No pitch deck. No sales pressure. Just an honest conversation about your project.
Trusted by startups, scale-ups, and enterprises across France and internationally.