Research · Build · Deploy

Madusanka
Premaratne

Applied AI Researcher

Building AI systems grounded in research — privacy-preserving LLMs, semantic generalization, and on-device agentic architectures.

Privacy-First LLM Systems

Building large language models that respect user privacy isn't just ethical—it's essential for sustainable AI adoption and trustworthy systems.

Differential Privacy

Add statistical noise to provide mathematical privacy guarantees while maintaining model utility for downstream tasks.

Federated Learning

Train models across decentralized devices without exchanging raw data, keeping sensitive information local.

On-Device AI

Deploy models directly to user devices eliminating data transmission risks while ensuring privacy.

Data Minimization

Collect only essential data to reduce attack surface and privacy risks by design.

Secure Enclaves

Use hardware-based trusted execution environments to protect data during processing.

Model Watermarking

Embed detectable markers in models to track usage and prevent unauthorized distribution.

The Cost of Ignoring LLM Privacy

Privacy Violations

LLMs can memorize and leak sensitive personal data including private conversations, financial information, health records, and family secrets—leading to identity theft, blackmail, and irreparable harm.

Business Impact

Proprietary data and trade secrets become training leaks. One breach can destroy competitive advantage, trigger GDPR/CCPA fines (up to 4% of revenue), and permanently damage customer trust.

Personal & Family Harm

Private family discussions, medical consultations, and financial matters become training data—potentially exposing your most intimate details to strangers through AI responses.

Ready to build AI systems that earn trust through robust privacy protections?

What I Build

Services grounded in active research — not packaged templates. Every engagement starts with understanding the real problem.

Research-backed

AI Privacy & Compliance Consulting

Design and implement query-time privacy frameworks for LLM applications — semantic generalization, data minimization, and GDPR-compliant AI pipelines without sacrificing utility.

PythonLangChainDifferential Privacy Frameworks+4 more
Learn More
Production-grade

AI Knowledge & Retrieval Systems

Build multi-agent retrieval-augmented generation systems for enterprise use — from architecture design through production deployment, including on-device and edge-first configurations.

LlamaIndexLangChainPostgreSQL (pgvector)+5 more
Learn More
Custom-built

AI Search & Text Intelligence Consulting

Apply semantic generalization, embedding strategies, and NLP pipelines to solve real classification, extraction, and search problems — grounded in current research, not off-the-shelf demos.

Hugging Face (Transformers)spaCyScikit-learn+5 more
Learn More
Privacy-first

On-Device & Data-Sovereign AI Consulting

Move inference off the cloud — design on-device agentic systems that preserve data sovereignty, reduce latency, and achieve inherent compliance. No third-party data exposure.

Ollama (local runs)Llama.cppONNX Runtime+4 more
Learn More
Strategic

AI Strategy Consulting

Define your AI research agenda, evaluate model capabilities, and translate academic findings into product strategy. Research collaborations, manuscript preparation, and AI readiness assessments.

Google Vertex AIOpenAI / Anthropic APIsWeights & Biases (eval tracking)+3 more
Learn More
End-to-end

Enterprise AI Integration

Integrate LLM inference pipelines and multi-agent systems into existing products — from API design and prompt engineering through evaluation, monitoring, and responsible deployment.

FastAPI / Express APIsLangfuse / Phoenix (LLM observability)Docker+4 more
Learn More

Sovereign & Enterprise Tech Stack

We leverage production-grade platforms and open-source models to build secure, private, and high-performance AI solutions.

Python
LangChain
LlamaIndex
HuggingFace
Ollama
PyTorch
Docker
Postgres
10+
Years in Industry
4
Active Research Projects
2
University Collaborations
95.1%
Privacy Preservation Rate
Applied AI Research & Founder

Bridging the gap between Academic Research and Enterprise Application

I am a Founder, CEO, and applied AI researcher with over a decade in enterprise software. I lead the research agenda at Knivok, focusing on privacy-preserving LLMs, query-time semantic generalization, and on-device agentic architectures.

My work translates theoretical models into production-ready software systems for clients globally, backed by first-class academic credentials from the University of Jaffna and London Metropolitan University.

Active Research Collaborations

Applied AI Publications & Experiments

2025 – 2026Active collaboration

EdgeTal

Lead Researcher & Corresponding Author

On-device agentic RAG system for privacy-preserving talent discovery — full retrieval and inference pipeline at the edge, zero candidate data transmitted to the cloud. Presented at EICON 2026 (ESOFT International Conference), Kandy — awarded Best Poster Presenter.

Zero
Candidate data transmitted to cloud services
On-Device
Full agentic RAG pipeline — retrieval, reasoning, generation — at the edge
2025Active collaboration

Gen Z Job Commitment Study

Principal Researcher

Quantitative study of 386 Gen Z employees across WSO2, IFS R&D, Knovik, and Prime One Global, testing four determinants of job commitment via SPSS correlation and chi-square analysis. Manuscript in preparation for AIRC 2026.

386
Gen Z respondents across leading Sri Lankan IT firms
4
Determinants tested via correlation & chi-square analysis