EdgeTal: On-Device Agentic RAG for Privacy-Preserving Talent Discovery
EICON 2026 — ESOFT International Conference · 30 August 2026
Co-authors
Introduction: Every time a recruiter uploads a resume to a cloud-based hiring platform, the candidate's personal data leaves their control. AI-powered screening has made hiring faster, but by routing sensitive information through external servers, it trades off against modern privacy law. Most mobile recruitment tools also still rely on exact keyword matching rather than semantic understanding.
Objectives: This study asks whether a smartphone can perform intelligent candidate search and analysis entirely on device, without any cloud connection.
Methods: EdgeTal was developed as a native Android application built around a three-stage on-device Agentic RAG pipeline. Recruiter queries are encoded as semantic embeddings, matched against candidate profiles through vector similarity search, and interpreted by a quantised Gemma-2B (Int4) language model running entirely on the device. The system was evaluated on 1,500 resumes across two devices, a Google Pixel 7 Pro and a Xiaomi Redmi Note 7.
Results: Semantic search responded in under 100ms on the Pixel 7 Pro and under 300ms on the Redmi Note 7. For abstract and role-based queries, keyword matching returned no relevant results, whereas semantic retrieval consistently surfaced relevant candidates.
Conclusions: These results show that privacy-preserving, intelligent recruitment can run on existing mobile hardware rather than dedicated cloud infrastructure, given an appropriate on-device architecture.
Outcome: EdgeTal was presented as a poster at EICON 2026, the ESOFT International Conference held at ESOFT University in Kandy on 30 August 2026, where it received the award for Best Poster Presenter in the Computer Science, Artificial Intelligence and Information Systems track.
Key findings
- Presented at EICON 2026, the ESOFT International Conference, on 30 August 2026
- Won Best Poster Presenter — Computer Science, Artificial Intelligence and Information Systems
- Semantic search under 100ms on a Pixel 7 Pro, under 300ms on a Redmi Note 7
- Evaluated on 1,500 resumes with zero candidate data leaving the device