Hire the Best Automation Engineers
in Sri Lanka

Did you know businesses lose 30–40% of productive hours to tasks that AI Agents can handle automatically 24/7, without error, without overtime? I build production-grade AI Agent systems that eliminate manual work, automate complex workflows, and integrate directly into your existing tools and operations. From LangGraph multi-agent pipelines to n8n automation and real-time voice agents — everything I deliver goes into production, not just a demo. 100% Job Success Score · Top Rated on Upwork · 10+ production deployments across real estate, healthcare, SaaS, and service businesses. ✅ What You'll Gain by Working With Me: 💰 Cut Operational Costs Replace expensive manual workflows with AI agents that scale. My systems reduce support overhead, automate lead handling, and eliminate data entry — while improving speed and accuracy across your operations. ⏱ Save Your Team Hundreds of Hours Free your team from repetitive tasks. My agents handle customer queries, document search, lead qualification, appointment booking, and CRM updates — instantly and accurately, around the clock. 📈 Scale Without Hiring AI agents operate 24/7 without fatigue. Scale your support, sales, and operations withoutincreasing headcount or overhead. 🎯 Smarter Customer Experiences Deploy always-available AI agents that give your customers real-time answers, handle inquiries, and guide them through your process — with zero wait time. 🔄 Deep Integrations, Not Just Chatbots I connect your AI agents directly to your CRM, APIs, databases, and internal tools — so everything runs seamlessly in the background without manual handoffs. 🧠 What I Build: AI Agent Systems (LangGraph) Multi-step agentic workflows with tool routing, memory, and real API integrations — far beyond simple chatbots RAG Knowledge Agents Agents trained on your documents, FAQs, and databases that retrieve accurate answers instantly Workflow Automation (n8n · Make) End-to-end pipelines connecting your tools, CRM, webhooks, and APIs with zero manual intervention Voice AI Agents (Retell AI · Vapi · Twilio) AI phone agents that answer calls, qualify leads, book appointments, and trigger follow-up actions automatically WhatsApp & Messaging Agents AI agents connected to WhatsApp Business API, Telegram, and Slack — handling inquiries, orders, and support CRM Automation (GoHighLevel · HubSpot) Smart lead routing, pipeline management, follow-up sequences, and contact syncing running automatically 🛠 Tech Stack: Agents & AI: LangGraph · LangChain · OpenAI API · RAG pipelines · Prompt Engineering Automation: n8n · Make · Zapier · Webhooks Voice: Retell AI · Vapi · Twilio · LiveKit · ElevenLabs · WebRTC Messaging: WhatsApp Business API · Telegram · Slack Backend: Python · FastAPI · Supabase · PostgreSQL CRM: GoHighLevel · HubSpot · Salesforce 📊 Results From Real Deployments: ✅ LangGraph AI Agent: Automated 7-intent WhatsApp ordering system for a restaurant client zero manual order handling ✅ Voice AI Pipeline: Built self-hosted voice agent at $0.02/min vs $0.08–$0.10/min with third-party providers — 75% cost reduction for the client ✅ RAG Knowledge Agent: Deployed on cloud platform reduced internal query resolution time by 60% ✅ Outbound Voice Agent: Built AI staffing pipeline that autonomously contacts candidates qualifies them, and updates CRM — replacing 40+ hours/week of manual outreach ✅ Computer Vision Pipeline: Real-time YOLO-based detection system deployed on edge hardware for industrial monitoring 💼 Who I Work Best With: Startups building AI-first products or MVPs SaaS companies adding LLM features to existing platforms Service businesses automating sales and support ops Agencies needing white-label AI agent builds Founders who want production systems, not prototypes 📦 What You Get: Custom AI Agent built specifically for your use case Clean, documented, production-ready code Full integration with your tools, APIs, and workflows Testing with your real data before handoff Deployment-ready — hosted or self-hosted Optional ongoing support and optimisation 🚀 Let's Build Your AI Agent System Whether you need a LangGraph agentic workflow, an n8n automation pipeline, a RAG knowledge base, or a voice AI agent — I'll design and deploy a system that delivers real, measurable business impact. 📩 Send me a message or click "Invite to Job" let's talk about what we can automate for you. AI voice agent development, AI voice agents, custom AI voice agents, AI phone agents, conversational AI, voice AI development, AI call automation, AI IVR systems, Twilio voice, Twilio IVR, Twilio automation, Retell AI, Retell AI development, Vapi AI, Vapi voice agents, LiveKit voice AI, WebRTC voice agents, real-time voice AI, AI receptionist systems, Claude Code, Claude Code automation, Claude Code AI agents, Claude Code workflows, Claude Code prompt engineering, Claude Code integrations, Claude Code API integration whatsapp bot

I build Python automations and API integrations that take repetitive operations off your team - scripts and backends that run on schedule, handle their own errors, and don't need babysitting. CORE PYTHON AUTOMATION API integrations between systems that don't talk to each other, scheduled jobs, browser automation and scraping with Playwright, and data transformation scripts with real error handling and logging built in. Recent: an automated crypto trading bot - Flask API on Azure with a real-time dashboard. It has run unattended for 18 months and executed 654 trades, 405 of them profitable. Eighteen months of uptime is the part I'm proud of: it handles its own failures instead of waking someone up. APPLIED AI RAG pipelines over private documents, FastAPI backends for AI tools, and LLM integrations using LangChain and vector databases (pgvector). - An offline RAG assistant indexing 70GB of Wikipedia ZIM archives, running fully local with no internet connection - A knowledge system over 11,400 notes doing relation mapping and vector search (FastAPI, PostgreSQL/pgvector, Redis, Celery) - A production RAG system for business analysis, delivered ahead of schedule and rated 5.0 TRACK RECORD 100% Job Success. Both completed contracts rated 5.0 - "a clear communicator and delivers prior time perfectly." I also ship production software outside automation: a POS system running in 100 shops, and an Android camera app published on the Google Play Store. That background is why deliverables come with clean architecture and documentation, not just a folder of scripts. HOW I WORK Fixed scope, defined deliverables, and a working prototype before you commit to the full build. If you have a manual process eating hours every week, tell me what it is and I'll tell you straight whether it's worth automating.

I convert your vision models from a notebook executable file to a production ready application. The real reason you cannot run your custom vision models with real-time accuracy and latency is the un-optimized tech stack and inconsistent training data. What I Build and Deliver: ✅ Dataset annotation and analysis (OpenCV, Roboflow) ✅ Object detection & segmentation | YOLO, RT-DETR, SAM ✅ ByteTrack, BoT-SORT based multi-object tracking ✅ Pose estimation & motion analysis using YOLO-pose, MediaPipe ✅ Application specific feature extraction (e.g. polygon zone based counting) ✅ Model optimization for high speed inference through OpenVINO, TensorRT, ONNX, and FP16/INT8 quantization ✅ Edge deployment on Jetson Orin, Raspberry Pi, Mobile phones ✅ LLM agent integration for alert automation and reasoning ✅ Real-time inference (10 - 30 FPS) and (50 - 200 ms) latency - depends on the hardware stack I am an Engineer with 2+ years hands-on experience in deploying Machine Vision pipelines under heavy real-world lighting and occlusions, which are the key practical issues most engineers don't solve. Domain Expertise: ➡️ Intersection traffic motion analysis (delay times, vehicle density/detection zone) ➡️ Product anomaly detection, production line tracking, off-site reading of analog gauges, worker safety monitoring ➡️ Ball tracking for trajectory analysis, real-time pit lane monitoring ➡️ Theft detection, shelf monitoring at retail stores ➡️ Fabric edge detection for automated sewing, depth based grasp estimation with 3D cloud generation ⚙️ Technical Stack: Python, C++ | OpenCV | Pytorch, TensorFlow | YOLOv5, YOLOv8, YOLOv11, YOLO26 | DeepSORT, ByteTrack, BoT-SORT | RT-DETR, RF-DETR | MediaPipe, OpenPose | FastAPI, Docker, AWS SageMaker | ONNX, OpenVino, TensorRT, CoreML, NCNN | Roboflow, CVAT, LabelImg | NVIDIA Jetson, Raspberry Pi 5, Coral TPU | LangChain, Claude, Gemini, GPT 📩 Let's talk if you have a project or an idea that involves visual data. I will layout my technical approach and we can discuss any alterations before you commit to the project.

🌟 ISTQB® Certified QA Engineer 🌟 Associate QA Engineer at IFS R&D International 🌟 1.5+ Years of Enterprise and Freelance QA Experience 🌟 Strong Manual Testing with Practical Automation Skills 🌟 5-Star Rated Upwork QA Tester About Me: I am an ISTQB®-CTFL certified Software Quality Assurance Engineer with hands-on experience testing real-world web applications in both enterprise and freelance environments. I currently work as a QA Engineer at IFS R&D International, where I contribute to enterprise-scale systems that require high reliability, accurate data handling, and disciplined release validation. Alongside my enterprise role, I actively support Upwork clients by performing structured manual testing, logging high-quality defects, and reviewing applications from an end-user perspective. I approach testing with a strong sense of ownership and responsibility toward the user experience, not just feature validation. I am comfortable working across different domains and can quickly adapt to new products, technologies, and business requirements. The following are some of my core competencies. • Manual QA testing of web applications • Functional, regression, smoke, and exploratory testing • Test planning, test case creation, and execution • End-to-end user flow validation and usability review • Defect tracking and reporting using Jira • Reviewing UI implementations against Figma designs • API testing using Postman (REST, authentication validation) • Basic database validation using SQL • Selenium WebDriver automation using Java • TestNG, JUnit, and Cucumber (BDD) based automation frameworks • Page Object Model for maintainable test automation • Cross-browser testing and basic Selenium Grid execution • CI-friendly testing practices and release validation • Experience working in Agile and DevOps-driven teams • Ability to work independently and collaborate effectively with developers 🏆 Reviews and feedback from my clients 🏆 ⭐⭐⭐⭐⭐ “Ravindu is an exceptional, highly impactful QA tester. He approached testing with a deep sense of ownership, curiosity, and responsibility toward the end user, not just the product. What truly sets his work apart is his ability to think like a real user while testing like an engineer. You didn’t just identify issues, you helped the team understand why they matter and how they affect user confidence and flow. Also looked into application code that helped in narrowing the fix time.” How I Work: I focus on clarity, consistency, and accountability. You can expect well-documented test cases, clear defect reports, timely communication, and honest progress updates. I test beyond happy paths and always explain the real impact of issues so teams can prioritize fixes effectively. If you are looking for a QA engineer who thinks like a user, tests like an engineer, and takes responsibility for product quality, I would be happy to discuss how I can support your project.