Winner, HackaDev 2018
2018National Youth Social Innovation Challenge, organized by ICTA and UNDP Sri Lanka.
About
AI Engineer, Agentic AI & LLM Systems · Dubai, UAE
I'm Aadhil, an AI Engineer based in Dubai with over five years of experience taking AI systems from first prototype to production. I specialize in agentic AI: designing and shipping multi-agent systems, LLM-powered applications, and the infrastructure that keeps them reliable at scale, not just in notebooks.
I began my career in data analytics and machine learning before moving into generative AI, building everything from RAG-based chatbots and document intelligence platforms to real-time voice agents and multi-agent workflows. Along the way I have worked across telco, fintech, and legal tech, which has shown me how agentic AI holds up under real-world constraints.
What interests me most are the parts of agent systems that never show up in a demo: reliable tool use, context engineering, evaluation loops that catch regressions before users do, and the observability to debug a multi-step reasoning chain when something goes wrong. In production, that means designing guardrails and fallbacks, tuning retrieval quality, managing latency and token budgets, and watching how agents behave long after launch. Just as important to me is building AI people can trust: explainable, fair, and evaluated before it ships.
I deliver enterprise AI solutions end to end, from architecture to deployment: data pipelines and vector search, model serving, containerized microservices, and the monitoring that keeps it all running. I have led cross-functional teams of software, frontend, and DevOps engineers to ship this kind of work.
Outside of work, I write about AI engineering, from agent architectures and RAG systems to the production patterns tutorials usually skip. Sharing what I learn as I build is how I contribute back to the community.
Experience
Artificial Intelligence Engineer (Lead Developer)
The Law Reporters (TLR One) · Dubai, UAE
February 2025 – Present
- Developed a multi-agent Legal AI platform that automates document analysis, legal research, drafting, and client interactions, with an LLMOps-based evaluation and monitoring framework for production reliability, deployed as scalable FastAPI microservices on containerized infrastructure.
- Designed and deployed a knowledge-driven CRM chatbot using an advanced RAG architecture and LangChain to deliver accurate, context-aware responses from CRM data, leading its end-to-end development and production maintenance.
- Built a GenAI-powered credit portfolio analyzer that automates debt portfolio insights and risk prioritization, reducing manual review time by 45% and improving collection efficiency by 35%.
- Developed a Legal Matter Analyzer integrated with the CRM using LangChain, Azure OpenAI, Django, and PostgreSQL, delivering intelligent classification and recommendations with 92% accuracy and cutting processing time by 40%.
- Architected production-grade GenAI microservices for email automation, sentiment analysis, timesheet summarization, and speech-to-text pipelines, improving operational productivity by 38% and cutting manual workload by 50%.
- Built an AI-powered outbound voice calling agent using Twilio and OpenAI with real-time text-to-speech, enabling human-like automated conversations for customer outreach.
- Engineered a Power BI analytics dashboard with real-time KPIs and a scalable FastAPI analytics microservice for dynamic data visualization across multiple sources.
Data Scientist
Axiata Digital Labs · Colombo, Sri Lanka
December 2021 – January 2025
- Developed an LLM-powered microservices generator and SRS document generator using LangChain, Azure OpenAI, and advanced prompt engineering, significantly improving developer productivity and code generation quality.
- Designed and implemented a RAG-based document chatbot enabling interactive Q&A on uploaded documents.
- Built customer segmentation clustering models that reduced marketing expenditure by 30% through precise targeting, and implemented a credit scorecard model with a dynamic credit limit decision engine.
- Established MLOps pipelines on AWS SageMaker for automated model training and deployment, and built AutoML workflows with PyCaret.
- Designed cloud-based ETL pipelines (Azure Data Factory, Databricks, Spark, Airflow, Snowflake) for forecasting, an information security data lake, and modernized KPI reporting.
Business Intelligence and Analytics Intern
Dialog Axiata PLC · Colombo, Sri Lanka
November 2020 – December 2021
- Performed customer segmentation based on buying power to identify high-potential targets and optimise marketing strategies.
- Developed a rule-based product preference prediction model for non-sachet users, increasing sales by 60%.
- Researched and engineered a deep learning recommendation engine achieving 85% accuracy on 500,000 customer records for new customer targeting.
- Conducted exploratory data analysis (EDA) on customer behavioural data to deliver actionable insights to product teams.
Skills & Tools
LLM & Agent Frameworks
LangChainLangGraphLangChain.jsLlamaIndexHaystackCrewAIMicrosoft AutoGenGoogle ADKMCP
Models & Providers
Azure OpenAIOpenAIGoogle GeminiHugging FaceGroqOllama
RAG & Vector Databases
PineconeChromaQdrantFAISSRedis
Voice AI & Real-Time Agents
LiveKitTwilioDeepgram
Machine Learning & Data Science
PythonPyTorchTensorFlowKerasScikit-learnXGBoostLightGBMPyCaretOpenCVPandasNumPyStatistical ModelingA/B Testing
Backend & Web
TypeScriptFastAPIDjangoGoNode.jsNext.jsReact
MLOps & Observability
DockerKubernetesGitHub ActionsMLflowDVCWeights & BiasesArize PhoenixLangfuseGrafanan8nLinux
Cloud & Data Engineering
AWSAWS SageMakerAWS BedrockAzureAzure SynapseGCPApache SparkApache AirflowDatabricksAzure Data FactoryAWS GlueSnowflakePostgreSQLMySQLMS SQLOracle SQLPower BITableau
Education
Bachelor of Information Communication and Technology (Hons)
Faculty of Technology, Rajarata University of Sri Lanka
Relevant Coursework: Data Science, Artificial Intelligence, Software Engineering, Computational Mathematics, Computational Statistics, Internet of Things, and Robotics.
Advanced Diploma in Data Science
National Institute of Business Management, Sri Lanka
May 2019 – December 2020
Awards & Hackathons
1st Place, HaXmas 19 Hackathon
2019Annual ideathon organized by the Rotaract Club of IIT Sri Lanka.
Finalist, Mobitel SMART SRI LANKA Hackathon
2019Overnight hackathon at the Ancient Technology Museum, Polonnaruwa, organized by the Mobitel Innovation Center.
Finalist, Mobitel NB-IoT Hackathon
2018Sri Lanka's first NB-IoT forum and hackathon, organized by the Mobitel Innovation Center.
Semi-Finalist, HackX 2020
2020Inter-University Startup Challenge, organized by the University of Kelaniya.
Semi-Finalist, HackX 2019
2019Inter-University Startup Challenge, organized by the University of Kelaniya.
Participant, SL IoT Hackathon 2020
2020Organized by the Department of Computer Science and Engineering, University of Moratuwa.
Participant, Global Game Jam 2019
2019Organized by Sri Lanka Unity Developers and Arimac Lanka.
Certifications
- Claude Certified Architect - Professional (Reading)Anthropic
- DeepLearning.AI TensorFlow Developer Professional CertificateCoursera
- Machine Learning Engineering for Production (MLOps) SpecializationCoursera
- Google Cloud Machine Learning Operations (MLOps): Getting StartedCoursera
- Practical MLOps for Data Scientists & DevOps on AWSUdemy
- LangChain: Develop LLM-Powered ApplicationsUdemy
- LangChain, Pinecone & OpenAI: Build Next-Gen LLM AppsUdemy
- Azure Data Factory for Data EngineersUdemy
Get in touch
I'm currently open to collaborations and interesting projects. Whether you have a question, want to discuss AI systems, or just want to say hi, reach out.