Madusanka Premaratne
Available for Advisory & R&D Engagements

Applied AI Research · Privacy-Preserving LLMs · Agentic RAG

Madusanka Premaratne — Applied AI Researcher & Founder

Building production-grade, privacy-preserving AI architectures, semantic generalization pipelines, and on-device agentic systems. Founder & CEO of Knivok.

Selected research & work

View all research →

Founder & CEO at Knivok · Applied AI Researcher · Best Poster Presenter at EICON 2026 · Accepted Author at AIRC 2026 · 10+ Years Enterprise Software & AI Systems

Core Research Agenda

Privacy-First LLM Systems

SemanticGuard

Query-Time Semantic Generalization

SemanticGuard's core method: sensitive fields are generalized at the moment of the query — before anything reaches a cloud LLM — rather than redacted after the fact. Evaluated on 32,593 queries at 95.1% data protection with 93.4% utility preserved.

EdgeTal

On-Device Agentic RAG

EdgeTal's full retrieval, reasoning, and generation pipeline runs on local hardware. Zero candidate or user data is transmitted to any cloud inference endpoint — the architecture, not a policy, enforces this.

Architecture

Data Minimization by Architecture

Collecting less, and generalizing what is collected, beats collecting everything and relying on access controls or post-hoc redaction to contain it.

Benchmark

Utility-Preserving, Not Just Private

Privacy techniques that gut model usefulness don't get adopted. The research question is the tradeoff itself — SemanticGuard measures both protection and utility simultaneously.

Edge AI

Edge-First Inference

Quantized models running on commodity hardware eliminate the round-trip to a third-party API entirely — no data residency ambiguity, no inference-time exposure to a cloud provider.

Compliance

GDPR-Class Compliance by Design

When raw data never leaves the device, there's no cross-border transfer and no third-party sub-processor to disclose. Compliance follows from the architecture.

Why Privacy-First Architecture Matters

Data Leakage via Training

LLMs can memorize and resurface fragments of the data they were trained or fine-tuned on. Without an architectural safeguard, sensitive inputs carry real statistical extraction risk.

Regulatory Exposure

GDPR/CCPA-class regimes attach real liability to cross-border transfer and undisclosed retention. Architecture that avoids transmission avoids the exposure by design.

Trust & Adoption

Enterprises evaluating AI vendors increasingly ask where their data goes before what the model can do. An architecture that answers that cleanly is a competitive advantage.

10+
Years in Industry
4
Published & Accepted Papers
Privacy & Edge AI
Research Tracks
95.1%
Semantic Privacy Rate
Applied AI Research & Leadership

Bridging the gap between academic research and production enterprise AI

I am Founder, CEO & Chief AI Research Officer at Knivok, leading research in query-time semantic generalization, privacy-preserving LLMs, and on-device agentic architectures.

My work translates theoretical privacy guarantees into deployable software for global enterprises, backed by first-class academic credentials from the University of Jaffna and London Metropolitan University.

Working on something? Let's talk.

Pick a call option that fits — a first exploratory conversation, a build to scope, or an AI readiness check.