Privacy-First AI Recruitment

Find talent.
Keep data on device.

EdgeTal is an AI-powered recruitment tool that runs entirely on your phone. Semantic search, candidate analysis, zero cloud dependency. Your data never leaves your device.

Read the Research
edgetal — semantic search
query › “Senior developer with leadership potential”
searching 2,484 candidates locally...
✓ 10 matches found in 52ms
cloud requests: 0  |  data transmitted: 0 bytes
_
How It Works

Three-stage agentic pipeline. Fully offline.

🧠

Plan — Understand Intent

Natural language queries are converted into 512-dimensional semantic vectors using on-device MediaPipe embeddings. No keywords needed.

🔍

Decide — Retrieve & Refine

Cosine similarity matching against locally stored candidate profiles. When confidence is low, an agentic loop autonomously reformulates the query.

Act — Analyse Candidates

A quantised Gemma-2B model generates structured candidate assessments with explainable reasoning: Thought, Evidence, Conclusion.

🛡️

100% On-Device Privacy

All processing happens locally. No cloud servers, no API keys, no data transfer. GDPR and CCPA compliant by architecture, not by policy.

📱

Built for Real Phones

Tested on mid-range Android hardware. Semantic search completes in under 200ms, even on devices with 4GB RAM.

📊

Dual-Layer Highlighting

Exact keyword matches in yellow. Semantic concept matches in blue. See what traditional search misses at a glance.

<90ms
Semantic search latency
5.8×
Faster than keyword matching
0
Bytes sent to cloud
2,484
Resumes tested on-device
📄

Research-Backed Architecture

EdgeTal's architecture is published in a peer-reviewed research paper presented at EICON 2026 (ESOFT International Conference). The system was empirically evaluated across two hardware tiers with benchmarks on retrieval accuracy, latency, scalability, and generative analysis quality.

EICON 2026 · ESOFT Uni, Sri Lanka · August 2026