Savindu Suranjith Thennakoon

About Me

Savindu Thennakoon

CSE Undergrad @ Uni of Moratuwa

Sri Lanka 3rd Year

I am a driven Computer Science and Engineering undergraduate at the University of Moratuwa, specializing in full-stack development, mobile engineering, and applied AI.

My passion lies in bridging the gap between cutting-edge AI research and practical applications. I have extensive experience building cross-platform mobile and web apps integrated with machine learning models and computer vision pipelines.

I am always looking for opportunities to apply robust problem-solving skills to innovative technical projects.

Full-Stack

MERN, React Native

Applied AI

LLM Agents, Computer Vision

Core Competencies & Stack

Technical Skills

Specialized tools, languages, and frameworks powering intelligent, scalable software solutions.

Flagship Specialization

AI & Neural Systems

Applied AI research, on-device vision, and autonomous agent orchestration.

LangGraph (Agents)

ChromaDB Vector Store

MediaPipe Pose

TensorFlow.js

RAG Architectures

Google GenAI / LLMs

Autonomous Workflow Deterministic State Machines

User Prompt → Vector Retrieve → Multi-Agent Action

Cross-Platform

Web & Mobile Apps

Responsive UI/UX, state management, and mobile cross-compilation.

React Native

React.js

Node.js / Express

Capacitor

RESTful APIs

Tailwind & CSS3

Database & Cloud

Databases & DevOps

Resilient data stores, containerization, and API verification pipelines.

PostgreSQL

MongoDB

Docker Container

Git & GitHub

Postman

MySQL

Engineering Foundation

Languages & System Architecture

Core programming languages, algorithmic problem solving, and microservices design.

Python

C++

JavaScript (ES6+)

TypeScript

Data Structures & Algorithms

Microservices Architecture

Selected Engineering Works

Featured Projects

Bridging cutting-edge machine learning and applied AI with resilient full-stack architectures.

Two-Phase Biometric Verified

Flagship Architecture 2026 Production

Smart Attendance Platform

An enterprise-grade cross-platform mobile ecosystem and live administrative dashboard. Engineered with dual-layer face recognition and GPS geofencing verification over a resilient microservices backend.

< 250ms Auth Latency

99.4% Face Match

15k+ Daily Events

React Native Node.js / Express Computer Vision MongoDB Docker

View Organization / Repository

biometric-auth.ts

const verifyBiometricScan = async (stream) => { const face = await cv.extract(stream); const geo = await gps.verifyRadius(); return microservice.authorize({ face, geo }); };

Geo-Biometric Match Status: Verified (Colombo Campus)

MediaPipe Real-time Pose

Mobile AI & Productivity

FitLock (AI App-Locker)

Locks distracting social applications until physical workouts are performed. Uses on-device MediaPipe Pose estimation to count exercise reps with zero cloud latency.

15 / 15 Squats Detected

98.6% Pose Confidence

🔓 App unlocked for 30 minutes!

React Tailwind CSS Capacitor MediaPipe Pose

View on Google Play

🏆 Global Rank #81 / 12,000+

Autonomous LLM Agent

HackerRank AI Support Agent

Terminal-driven autonomous support engineer automating enterprise ticket triage, query deduplication, and code debugging via deterministic state graphs.

LangGraph Agent State Machine

$ langgraph run triage_agent

[Ingest] Vector search: ChromaDB Top-5 matches

[Decision] Deterministic Router: Severity Critical

[Resolved] Ticket Auto-Triaged in 480ms

Python LangGraph ChromaDB Google GenAI

View Repository

Multi-Modal RAG & Vision Intelligence

Multi-Modal AI & Vision June 2026 Dual-Role Platform Docker Containerized

PrajaNavigator (AI Insight Platform)

Engineered an enterprise-grade Retrieval-Augmented Generation (RAG) system integrated with computer vision pipelines to ingest and analyze complex tabular, statistical, and document datasets. Delivers actionable intelligence through specialized user and administrative dashboards with a Python backend and containerized Docker Compose deployment.

< 350ms Hybrid RAG Latency

Dual UI User & Admin Portals

100% Dockerized Stack

Citizen Service AI Execution Flow (5-Step Pipeline)

Identify Service Identify government service needed

→

Dynamic MCQs Asks dynamic MCQs to determine specific situation

→

Create Forms Create required forms

→

Document Autofill Autofill using uploaded documents

→

Visit Roadmap Create visit roadmap and required document list

praja-navigator-pipeline.py 5-Step Pipeline Active

async def execute_citizen_workflow(user_query, uploaded_docs): service = await ai_agent.identify_government_service(user_query) situation = await mcq_engine.evaluate_dynamic_mcqs(service.id) forms = await form_builder.create_required_forms(situation) filled_forms = await vision_ocr.autofill_with_docs(uploaded_docs, forms) return roadmap_generator.create_visit_plan_and_doclist(filled_forms)

Dual Dashboards Active Role: Admin & Citizen Insights Synced

Python React Tailwind CSS Computer Vision / OCR RAG Embeddings Docker Compose PostgreSQL

View Repository (AGENTRIX26 QuadNova)

Hi, I'm Savindu

Full-Stack & AI Engineer

About Me

Savindu Thennakoon

Full-Stack

Applied AI

Technical Skills

AI & Neural Systems

Web & Mobile Apps

Databases & DevOps

Languages & System Architecture

Featured Projects

Smart Attendance Platform

FitLock (AI App-Locker)

HackerRank AI Support Agent

PrajaNavigator (AI Insight Platform)

Education & Involvement

Education

BSc (Hons) in Computer Science & Engineering

GCE Advanced Level

Leadership & Societies

Marketing Committee Lead

Co-Chair

Pillar Member

Taekwondo Team Member

Get In Touch