Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a Generative AI Engineer focused on production-grade LLMs, RAG, and agentic AI systems. I design and deploy scalable AI architectures using Azure OpenAI, AWS Bedrock, LangChain, Elasticsearch, and vector databases to deliver enterprise knowledge retrieval, recruitment automation, and AI-powered customer support. I thrive on building robust data pipelines, guardrails, and evaluation frameworks to minimize hallucinations and maximize relevance. In my work, I’ve shipped multi-modal extraction systems, hybrid retrieval pipelines, and memory-enabled conversational agents that handle tens of thousands of interactions monthly. I enjoy collaborating cross-functionally, guiding junior engineers, and optimizing costs and performance through thoughtful architecture and automation.…I am a Generative AI Engineer focused on production-grade LLMs, RAG, and agentic AI systems. I design and deploy scalable AI architectures using Azure OpenAI, AWS Bedrock, LangChain, Elasticsearch, and vector databases to deliver enterprise knowledge retrieval, recruitment automation, and AI-powered customer support. I thrive on building robust data pipelines, guardrails, and evaluation frameworks to minimize hallucinations and maximize relevance. In my work, I’ve shipped multi-modal extraction systems, hybrid retrieval pipelines, and memory-enabled conversational agents that handle tens of thousands of interactions monthly. I enjoy collaborating cross-functionally, guiding junior engineers, and optimizing costs and performance through thoughtful architecture and automation.

Prasad Chathuranga

AI Engineer, Data Scientist, Full Stack Developer, +2





I am a Generative AI Engineer focused on production-grade LLMs, RAG, and agentic AI systems. I design and deploy scalable AI architectures using Azure OpenAI, AWS Bedrock, LangChain, Elasticsearch, and vector databases to deliver enterprise knowledge retrieval, recruitment automation, and AI-powered customer support. I thrive on building robust data pipelines, guardrails, and evaluation frameworks to minimize hallucinations and maximize relevance. In my work, I’ve shipped multi-modal extraction systems, hybrid retrieval pipelines, and memory-enabled conversational agents that handle tens of thousands of interactions monthly. I enjoy collaborating cross-functionally, guiding junior engineers, and optimizing costs and performance through thoughtful architecture and automation.…I am a Generative AI Engineer focused on production-grade LLMs, RAG, and agentic AI systems. I design and deploy scalable AI architectures using Azure OpenAI, AWS Bedrock, LangChain, Elasticsearch, and vector databases to deliver enterprise knowledge retrieval, recruitment automation, and AI-powered customer support. I thrive on building robust data pipelines, guardrails, and evaluation frameworks to minimize hallucinations and maximize relevance. In my work, I’ve shipped multi-modal extraction systems, hybrid retrieval pipelines, and memory-enabled conversational agents that handle tens of thousands of interactions monthly. I enjoy collaborating cross-functionally, guiding junior engineers, and optimizing costs and performance through thoughtful architecture and automation.

Available to hire

I am a Generative AI Engineer focused on production-grade LLMs, RAG, and agentic AI systems. I design and deploy scalable AI architectures using Azure OpenAI, AWS Bedrock, LangChain, Elasticsearch, and vector databases to deliver enterprise knowledge retrieval, recruitment automation, and AI-powered customer support. I thrive on building robust data pipelines, guardrails, and evaluation frameworks to minimize hallucinations and maximize relevance.

In my work, I’ve shipped multi-modal extraction systems, hybrid retrieval pipelines, and memory-enabled conversational agents that handle tens of thousands of interactions monthly. I enjoy collaborating cross-functionally, guiding junior engineers, and optimizing costs and performance through thoughtful architecture and automation.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Data Engineer (Project-Based Contract) at SNAPDRUM LTD

September 1, 2025 - October 1, 2025

Architected a serverless ETL pipeline using AWS Step Functions to move data from Google Cloud Storage into Apache Iceberg tables. Eliminated persistent EC2 dependencies, significantly reducing cloud compute costs while maintaining high data availability.

AI Engineer | GenAI Solutions (Project-Based Contract) at Syntax Genie (Pvt) Ltd

July 1, 2025 - April 1, 2026

Led the development of Worklink, an award-winning AI recruitment platform. Built a multi-modal CV extraction system achieving 95%+ extraction accuracy and semantic JD-to-candidate matching using Elasticsearch and embeddings. Reduced AI infrastructure costs by 98% through workflow optimization and transcription automation. Developed EDUGATE CRM, a GPT-4o and Qdrant-powered RAG assistant handling 30,000+ monthly inquiries; implemented persistent memory and retrieval pipelines with robust data security and reliability.

External Research Co-Supervisor (Part-Time) at University of Moratuwa

January 1, 2025 - May 1, 2026

Co-supervised AI and NLP academic research projects, guiding model architecture design, evaluation methodology, RBAC implementation, and performance benchmarking.

Engineer – Data Engineering & AI (Full-Time) at MillenniumIT ESP

August 1, 2024 - April 1, 2026

Designed and delivered production-ready RAG systems using Azure OpenAI, LangChain, Qdrant, and Python, serving engineering teams across multiple business units and reducing engineering information discovery time from hours to seconds. Built hybrid retrieval pipelines across enterprise documents, improving retrieval precision and contextual relevance. Implemented human-in-the-loop evaluation frameworks to enhance response quality and reduce hallucinations; aligned model and inference optimization with scalability goals.

Trainee Data Engineer - AI Focus (Full-Time) at hSenid Mobile Solutions

January 1, 2023 - June 1, 2023

Designed and deployed a GenAI chatbot integrating speech recognition and NLP pipelines for telecom use cases. Led data science implementation for CodeFest 2023 (Top 5 Finalist), integrating Generative AI APIs into legacy telecom systems.

Python Developer (Freelance) at Fiverr (Freelance Services)

April 1, 2020 - January 1, 2023

Delivered 20+ Python-based automation, ML, and NLP systems for diverse clients, including supervised text classification and document processing pipelines. Designed model validation workflows with performance monitoring and evaluation metrics to ensure production readiness.