Final-Year Computer Engineering Undergraduate, University of Ruhuna.
Building production-ready AI systems
from models to scalable software.
Software Engineer • AI/ML • Agentic AI • RAG
AI & ML projects deployed end-to-end (training → API → UI)
Experience with real-time systems, pipelines & model persistence
Research-focused: Blockchain + GNNs for vehicular networks
Technical Arsenal
🧠 AI / ML Systems
- •Model training, evaluation & persistence
- •Pipelines (scikit-learn, custom preprocessing)
- •Computer Vision (OpenCV, real-time inference)
- TensorFlowPyTorchPython
🌐 Software Engineering
- •REST & real-time APIs (Node.js, Socket.io)
- •Frontend systems (React, Next.js, React Native)
- •Authentication, state management, scalability
- TypeScriptNode.jsNext.js
☁️ Dev & Ops
- •Dockerized services & containers
- •AWS deployment basics
- •Git-based collaboration & CI mindset
- DockerGitLinux
Work Experience
Software Engineering Intern
Capricon Solution Pvt Ltd • 6 Months
Developed and maintained enterprise-level solutions, specifically focusing on a robust Point of Sale (POS) system. Handled backend logic for inventory management, sales tracking, and reporting modules to support business operations.
Business Logic
Translated complex business requirements into clean, maintainable code within the MVC architecture.
Database Design
Managed relational databases (MySQL) for high-transaction environments (sales/inventory data).
Featured Projects
See allNeurospace
Built an AI-powered GraphRAG application enabling intelligent document ingestion, media transcription, and interactive knowledge graph visualization. Implemented a chat interface for contextual queries.
Key learning: Designed Graph retrieval-augmented pipelines and orchestrated data processing workflows using multiple AI models.
End-to-End MLOps Pipeline & Deployment
Architected a full-stack Machine Learning application with a CI/CD pipeline, Docker containerization, and production deployment on Render Cloud, moving beyond static notebooks.
Key learning: Implemented Containerization (Docker), Automation (GitHub Actions), and Deployment for a production-ready ML workflow.
Resume Optimizer
A Streamlit dashboard that parses resumes into JSON and gives an ATS score using Llama 3.
Key learning: Structured Output (JSON) and system prompts.
EV Charging Station Management Platform
Built a full-stack system enabling real-time charger availability, booking, and route-aware station selection. Implemented live updates using WebSockets and designed the backend.
Key learning: Designed real-time systems and managed state consistency across clients.
LiveTalk – Secure Real-Time Communication
Designed a multi-user chat system with message flows, and communication using Socket.io.
Key learning: Explored real-time scalability, message synchronization, and user presence management.
ContextIQ: RAG Document Assistant
Built a production-ready Retrieval-Augmented Generation (RAG) application enabling semantic search and Q&A over PDF documents. Integrated Google Gemini for high-dimensional embeddings and generation, with Pinecone managing vector storage.
Key learning: Implemented modern RAG architecture using LangChain, mastered handling vector embeddings (3072-dim), and solved production integration challenges like dynamic dimension resizing and namespace management.
Engineering Journal & Open Source
Current Focus
Building
Production-grade AI apps with clean APIs, observability, and predictable outputs.
Learning
LLM system prompts, structured JSON extraction, and evaluation for reliability.
Open To
AI/ML engineering, backend systems, and impactful product collaborations.
Open to Conversations
Always open to discussing AI systems, backend scaling, or new opportunities.