Mohamed Aadhil Imam
AI Engineer · Dubai, UAE
I'm Aadhil, a Dubai-based AI Engineer who turns ambitious AI ideas into working products. For over six years I've carried systems through every stage of their life, from the first rough experiment to a hardened service handling real users. Most of my work centers on autonomous agents: teams of AI agents that plan, call tools, and collaborate on complex tasks, the language-model applications built around them, and the engineering backbone that keeps everything stable, fast, and affordable as usage grows.
My path into this field began with data analytics and classical machine learning, which gave me a grounding in how data behaves before any model touches it. From there I moved into generative AI and have since built retrieval-powered chatbots, document intelligence platforms, voice agents that respond in real time, and workflows where several agents share the job. Doing this in telco, fintech, and legal tech taught me what strict regulation, messy data, and demanding users do to a design that looked perfect on paper.
The work I enjoy most is the part a demo never shows. Getting an agent to use its tools correctly every time, giving the model exactly the context it needs, running evaluations that flag a regression before a customer notices, and tracing a long chain of reasoning to find the step that went wrong: this is where a system earns its place in production. Day to day, that means building safety checks and fallback paths, sharpening retrieval quality, keeping response times and token costs under control, and studying how agents behave months after release. I hold the same standard for trust, so what I ship is explainable, fair, and tested before anyone depends on it.
I own enterprise projects from the first architecture sketch to the live deployment. That covers the full design of an AI system: data pipelines, retrieval with hybrid search and reranking, cost-aware model serving, agent orchestration, and the tracing and evaluation that keep it all in check. I've also led mixed teams of software, frontend, and DevOps engineers, keeping everyone aligned through delivery.
Away from client work, I write about AI engineering: how to structure agents, how to make retrieval systems accurate, and the production lessons that most tutorials leave out. Publishing what I learn while building is my way of giving back to the community that taught me.
Experience
SparkitArtificial Intelligence Engineer2026 – Present
Jul 2026 – Present · Dubai, UAE
- Built Gabi Studio, Sparkit's new AI design assistant, from scratch and took it to production on web, iOS, and Android, replacing the previous design agent as the main creative surface.
- Designed its multi-agent architecture: an orchestrator that works with the user and calls on research and analyst specialists, with every step graded by a separate judge model and repaired once if it fails.
- Cut the cost of a simple request by 70% while keeping performance consistent.
- Took users from a text prompt, catalogue item, or photo to a priced, production-ready tech pack in one chat, including multi-piece collections rendered in the background with automatic logo checks.
- Built an agent evaluation platform to compare models, run A/B tests, and evaluate the full system, and added evaluation loops inside the agent.
- Added memory layers so the agent recalls past designs, prices, and preferences across conversations, reusing earlier work at no extra cost.
- Built an agent ops platform to monitor, manage, and trace every agent, with per-turn cost and quality tracking, plus social media publishing and a behavior-based notification aggregator.
The Law Reporters (TLR One)Artificial Intelligence Engineer (Lead Developer)2025 – 2026
Feb 2025 – Jun 2026 · Dubai, UAE
- 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.
Axiata Digital LabsData Scientist2021 – 2025
Dec 2021 – Jan 2025 · Colombo, Sri Lanka
- 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.
Dialog Axiata PLCBusiness Intelligence and Analytics Intern2020 – 2021
Nov 2020 – Dec 2021 · Colombo, Sri Lanka
- 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.
What I do
- Enterprise AI Solutions
- End-to-end delivery, from architecture and system design to production deployment and monitoring.
- Agentic AI & Multi-Agent Systems
- Designing agent workflows that reason, plan, and use tools reliably in production.
- RAG & LLM Applications
- Building retrieval-grounded chatbots and enterprise document intelligence platforms.
- Conversational & Voice AI
- Creating intelligent assistants and real-time voice agents with speech pipelines.
- LLM Engineering
- Fine-tuning, evaluation, and cost and latency optimization for LLM workloads.
- MLOps & AI Infrastructure
- Shipping containerized AI microservices with CI/CD, monitoring, and observability.
- Data Science & Analytics
- Predictive modeling, A/B testing, and dashboards that drive business decisions.
Skills & tools
- Languages
- PythonTypeScriptGoSQL
- LLM & Agent Frameworks
- Pydantic AILangGraphLangChainLangChain.jsVercel AI SDKMCPLlamaIndexCrewAIMicrosoft AutoGenGoogle ADKHaystack
- Models & Providers
- OpenAIAzure OpenAIAnthropic ClaudeGoogle GeminiDeepSeekGroqOpenRouterHugging FaceOllama
- Agent Evaluation & Observability
- LLM-as-a-JudgeModel A/B TestingAgent TracingLogfireLangfuseArize PhoenixPostHog
- RAG & Vector Databases
- PineconeQdrantChromaFAISSRedis
- Voice AI & Real-Time Agents
- LiveKitDeepgramTwilio
- Backend, Web & Mobile
- FastAPINode.jsHonoDjangoNext.jsReactReact NativeExpoSupabase
- Cloud Platforms
- AWSAWS ECSAmazon S3AWS BedrockAWS SageMakerAzureGCP
- MLOps & Infrastructure
- DockerKubernetesCI/CDGitHub ActionsMLflowWeights & BiasesDVCGrafanan8nLinux
- Data Engineering & Databases
- Apache SparkApache AirflowDatabricksSnowflakeAzure Data FactoryAzure SynapseAWS GluePostgreSQLMySQLMS SQLOracle SQL
- Machine Learning & Data Science
- PyTorchTensorFlowKerasScikit-learnXGBoostLightGBMPyCaretOpenCVPandasNumPyStatistical ModelingA/B TestingPower 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.
- May 2019 – Dec 2020
Advanced Diploma in Data Science
National Institute of Business Management, Sri Lanka
Awards & hackathons
- 2018
Winner, HackaDev 2018
National Youth Social Innovation Challenge, organized by ICTA and UNDP Sri Lanka.
- 2019
1st Place, HaXmas 19 Hackathon
Annual ideathon organized by the Rotaract Club of IIT Sri Lanka.
- 2019
Finalist, Mobitel SMART SRI LANKA Hackathon
Overnight hackathon at the Ancient Technology Museum, Polonnaruwa, organized by the Mobitel Innovation Center.
- 2018
Finalist, Mobitel NB-IoT Hackathon
Sri Lanka's first NB-IoT forum and hackathon, organized by the Mobitel Innovation Center.
- 2020
Semi-Finalist, HackX 2020
Inter-University Startup Challenge, organized by the University of Kelaniya.
- 2019
Semi-Finalist, HackX 2019
Inter-University Startup Challenge, organized by the University of Kelaniya.
- 2020
Participant, SL IoT Hackathon 2020
Organized by the Department of Computer Science and Engineering, University of Moratuwa.
- 2019
Participant, Global Game Jam 2019
Organized 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
Find me online on LinkedIn X GitHub Kaggle Medium, grab my resume, or send me an email.