Hire the Best Artificial Intelligence Engineers

🌟 Message me if you're interested in automating your business using AI/ML tools! I can help support and streamline your decision-making processes. 💡 I'm a ML engineer with relevant experience of AI integration into business. Here’s a core set of services I offer: 🔸 Agent end-to-end development and deployment with both low and high code frameworks. 🔸 WhatsApp/Telegram chatbots, with RAG, grounding architecture, using vector databases like Pinecone or ChromaDB. 🔸 LLM integration, using public APIs like OpenAI, VertexAI, AWS SageMaker, or Claude, as well as domain-specific fine-tuning. 🔸 Data collection and ETL using tools like Apify, Selenium, BeautifulSoup, requests. 💻 Tech Stack: Programming languages: Python Agent development: OpenAI, VertexAI, AWS SageMaker, Claude APIs, Pinecone, ChromaDB, LangChain, LangGraph, Hugging Face Transformers, Ollama Agent monitoring: LangFuse, LangSmith Deep Learning/ML: PyTorch, TensorFlow/Keras, scikit-learn, pandas, matplotlib/seaborn, NumPy Cloud services: AWS, GCP/GCS, Snowflake Databases: MySQL, SQLite, PostgreSQL, SnowflakeDB, MongoDB Back-end/API: Flask, FastAPI, Django, asyncio, multiprocessing Automation (bots): Telebot, Aiogram, PyWa, n8n, Zapier, Make, ElevenLabs Data scraping: Apify, requests, bs4, Selenium/ChromeDriver Version control: Git, Github, CI/CD (Github actions or gitlab)

I am a final year BSc Computer Engineering undergraduate at the University of Jaffna, Sri Lanka, with hands on experience in Artificial Intelligence, Machine Learning, AI automation, chatbot development, and full stack software engineering. I specialize in building practical AI powered applications that combine modern web development with Generative AI, LLMs, RAG pipelines, AI agents, voice technologies, NLP, and production ready backend systems. My main focus is helping clients turn ideas into real working systems such as AI chatbots, customer support assistants, document based RAG assistants, voice AI applications, workflow automation tools, SaaS platforms, and intelligent web applications. What I Can Help You Build: • Custom AI chatbots for websites, businesses, documents, and customer support • RAG based assistants using PDFs, websites, knowledge bases, videos, and business data • AI agents and automation workflows using LangChain, LangGraph, n8n, and API integrations • Voice AI systems using speech to text, text-to-speech, and real time conversation flows • NLP applications for text analysis, classification, summarization, and information extraction • Full stack AI web applications using React, FastAPI, Node.js, NestJS, and MERN stack • Machine learning models for classification, prediction, data analysis, and automation • Computer vision and image processing solutions for real-world AI use cases • SaaS style platforms, dashboards, admin panels, and scalable backend APIs Technical Skills: - AI & Generative AI: LLMs, RAG, AI Agents, Chatbots, Prompt Engineering, HuggingFace, Transformers, LangChain, LangGraph, Vector Databases, FAISS, ChromaDB. - Voice & NLP: Speech-to-Text, Text-to-Speech, Conversational AI, NLP Pipelines, Document AI, AI Assistants. - Machine Learning: Python, Scikit-learn, TensorFlow, Pandas, NumPy, Model Training, Model Evaluation, Data Preprocessing, Feature Engineering. - Full Stack Development: React.js, JavaScript, TypeScript, Node.js, Express.js, NestJS, FastAPI, Flask, Streamlit, MERN Stack. - Databases & Cloud: MongoDB, PostgreSQL, MySQL, Firebase, Supabase, AWS EC2, Vercel, Railway, HuggingFace, Firebase Hosting. - Automation & Integrations: n8n, REST APIs, third-party API integrations, workflow automation, email automation, Google Sheets automation. Why Work With Me: I understand both AI development and software engineering, which means I can build solutions that are not only intelligent but also usable, scalable, and reliable. I focus on clean code, clear communication, practical problem-solving, and building systems that create real business value. My internship and project experience have given me strong exposure to real-world development workflows, clean architecture, backend systems, AI integration, and production-ready application development. If you are looking for someone who can build AI chatbots, AI agents, RAG systems, voice AI tools, automation workflows, or full-stack AI applications, I would be happy to help bring your project to life. GitHub: UdaraChamidu Portfolio: udarachamidu.site

I help clients turn AI initiatives into operational systems that people can actually use and trust. I embed with client teams from discovery through rollout—identifying the right opportunity, designing the architecture, writing the code, integrating existing systems, and building the evaluations and human controls required for adoption. Clients bring me in when an important AI initiative needs more than a strategy deck or prototype. Because I handle both architecture and implementation, I can move from executive conversation to production code without the handoffs and delays of a conventional consulting team. CURRENT WORK • Clinical speech AI and multilingual interpretation For a multi-facility medical clinic in Dallas, I am building the data and model pipeline behind a self-hosted multilingual interpretation platform. The current work centers on collecting dialect-rich Arabic speech from clinic workflows and putting it through rigorous human transcription and review. The system supports segmentation, separate ASR and translation review, second-reader adjudication, consent controls, exact model and audio lineage, and reproducible dataset exports. Generic speech and translation APIs often struggle with regional dialects, medication names, dosages, negations, overlapping speakers, and the messy structure of real medical conversations. This pipeline gives the client a controlled way to evaluate and improve specialized models without allowing unverified AI output to become training truth. The same infrastructure can support Spanish, Vietnamese, Farsi, Urdu, and other high-need languages. The deployment roadmap includes model right-sizing, distillation, and quantization to reduce latency and operating cost across clinic locations. • AI property intelligence and geospatial reasoning Determining what can legally be built on a property is normally a fragmented expert-research process. It requires finding the correct municipal regulations, interpreting ambiguous zoning language, identifying the right parcel and district, understanding road frontage and neighboring conditions, and applying those rules to real geometry. For Plan AI, I built and productionized a property-intelligence engine that performs this work across municipal code, parcel geometry, road networks, building footprints, neighboring lots, FEMA flood data, and permit data. The system converts those sources into setbacks, buildable envelopes, risk signals, maps, and the evidence supporting each conclusion. Because an authoritative-sounding AI answer is not enough, I also built the anti-hallucination and geospatial evaluation layers. They reject invented ordinance language, unsupported calculations, unjustified assumptions, incorrect parcel or building matches, invalid envelopes, and contradictions between the model’s explanation and its result. The result is one evidence-backed workflow for understanding what constrains a property and what can potentially be built—while keeping uncertain cases visible for expert review. SELECTED EXPERIENCE • Led the development of an AI underwriting platform for a publicly traded lender with approximately $40M+ in annual revenue. It automated most application decisions while routing the hardest 10–15% to expert underwriters. • Designed and shipped a production payroll platform for Finally, a $100M Series B company, in approximately six weeks. • Helped build and stabilize Refine.ink, an AI peer-review platform used by faculty at leading U.S. universities. • Built SMART on FHIR and HL7 ADT healthcare integrations, voice-driven legal-intake systems, and computer-vision pipelines for identifying industrial weld defects only a few pixels wide. HOW I WORK I begin with the workflow, the people using it, the cost of failure, and the evidence the system must produce—not with a predetermined model or vendor. I can own the complete path from discovery through production, or embed with an existing team to resolve the critical architecture, integration, evaluation, and adoption challenges. As one Upwork client put it: “Got a week’s worth of work done in less than an hour due to Jonathan’s expertise. Would work with him again, no question.”

Most Machine Vision projects fail between the prototype and production. I've shipped 54+ that didn't. ⚙️YOLO Detection | Pose Estimation | Object Tracking | AI Agents | LLM Integration Sports & Fitness AI | CCTV & Surveillance AI | Retail AI | Healthcare AI You have a working concept... or a clear problem involving cameras, video, or image data. The challenge is making it fast, accurate, and stable under real-world conditions. Wrong framework choices. Inference too slow for live video. Models that break the moment lighting, angle, or environment changes. And systems that detect things but can't reason about them or act on them autonomously. That's exactly where most builds stall. I design and build real-time computer vision pipelines that go all the way... from model training to live deployment... and increasingly, from visual perception to autonomous AI agents that understand, decide, and narrate. LLM APIs (OpenAI, GPT-4o, Gemini, Claude) | AWS (EC2, S3, Lambda) | Azure Cloud Services | MLOps & API Integration | Model Deployment & Scaling While most CV engineers stop at training the model, I go further: → High-speed inference optimization using TensorRT, ONNX, OpenVINO, FP16/INT8 (up to 5× faster) → LLM agents integrated with vision pipelines for alerts, reasoning, and automation → Mobile AI deployment using Core ML (iOS) and TFLite (Android) with 10+ shipped apps → Edge AI deployment on Jetson, OpenVINO, CUDA, and embedded systems → End-to-end pipelines: data → training → optimization → real-time deployment Key Accomplishments: ⭐ $5M+ revenue from AI solutions ⭐ 100+ computer vision systems delivered ⭐ Built and launched 2 SaaS products ⭐ Real-time sports AI (7+ sports, 15+ teams) ⭐ 10+ mobile AI apps (iOS Core ML, Android TFLite) ⭐ Production AI for surveillance, industrial & safety use cases ⭐ Medical imaging AI deployed in 5+ hospitals ⭐ Up to 5× faster inference (ONNX, TensorRT, FP16/INT8) ⭐ Large-scale tracking & re-ID (1M+ labeled data) ⭐ Agentic AI systems for autonomous decision-making If you have read this far, please note that I appreciate you taking the time to learn about me. Personally, it’s been an amazing journey and knowledge exercise to get to this level of competence in AI and software development. Domain Expertise: ✅ athlete tracking | shot detection | scoring | drill analysis | pose estimation ✅ defect inspection | PPE compliance | staff monitoring | meter reading | quality control ✅ ANPR | crowd monitoring | people counting | intrusion detection | perimeter security ✅ tumor detection | ultrasound | X-ray/CT analysis | lesion segmentation | medical imaging ✅ aerial monitoring | traffic flow | license plate recognition | vehicle & accident detection ✅ customer analytics | receipt extraction | shelf monitoring | inventory tracking Tech Stack: YOLOv5–YOLOv8–YOLOv11, Detectron2, MMDetection, DeepSORT, StrongSORT, MediaPipe, OpenPose, Pose Estimation, Action Recognition, Segmentation (semantic & instance), OCR, anomaly detection, object tracking, PyTorch, TensorFlow, TFLite, Core ML, OpenCV, FastAPI, Flask, ONNX, TensorRT, OpenVINO, CUDA, AWS, Azure, GCP, edge AI, mobile AI, real-time inference, video analytics, AI automation, LLM integration (GPT-4o, Claude, Gemini, Groq), LangChain, LangGraph, CrewAI, RAG systems. 💬 If your project involves cameras, video, or images... and you need it fast, accurate, fully deployed, and intelligent enough to reason and act autonomously... I am the engineer you are looking for.

Ready to work. Ready to deliver. Ready to build just what you have in mind. I'm an Embedded Systems and Edge AI Engineer. I help founders, researchers, and businesses turn ideas into working hardware. Real devices that ship, run in the field, and survive the real world. What I build • IoT devices and smart products (ESP32, Raspberry Pi, Arduino, cellular, WiFi, OTA) • Edge AI systems running computer vision on low power hardware (YOLO, TensorFlow Lite, ONNX, Edge Impulse) • Custom firmware in C, C++, and Python, including RTOS and low power designs • Custom PCBs in KiCad and 3D enclosures in Fusion 360 • Autonomous robots with ROS 2, Nav2, SLAM, and reinforcement learning • Full stack hardware projects from schematic and BOM to deployed product Real work I have shipped • AquaGuard, a real time pool drowning detection system on Raspberry Pi using a custom trained YOLOv8s model, deployed live for a Nigerian client • FarmGuard, an edge AI cattle intrusion detection system, YOLOv11n at 92.70 percent mAP50 on Raspberry Pi with GSM alerts, validated across three Nigerian farms • PERWER, an IoT solar monitoring system on ESP32 with custom PCB and live cloud dashboard • CourierX, an autonomous delivery robot with full ROS 2 stack and RL based path planning • Diamon, a smart insole for diabetic foot ulcer detection with a 92 percent accuracy ML classifier, winner of the Ilorin Innovation Challenge Why clients work with me • Fast first response, usually within hours • Honest scoping and realistic timelines, even when the truth is harder to hear • Clear regular updates so you are never wondering where things stand • End to end delivery: firmware, hardware, cloud, deployment, documentation • Strong ownership when something goes wrong, no excuses • I genuinely love crazy projects. The weirder the brief, the more excited I get. Background B.Tech Mechanical Engineering (Second Class Upper) from Ladoke Akintola University of Technology. Director of Competitive Robotics at Aurora Robotics, mentoring 50 plus student engineers. Founder of Samfred Robotics. Winner of 10 plus engineering and innovation competitions including First Position at Ilorin Innovation Challenge, Hack4Livestock, 234 AI Hackathon, and NASA Global App Challenge (Benin). Let's talk Send me a message about your project, even if it is just a rough idea. I will reply quickly with honest feedback and a clear plan. Whether you need a single firmware fix or a full hardware product built from zero, I am ready to help you bring it to life.

I build production-ready RAG chatbots, voice AI agents, and autonomous AI systems — designed and deployed to hold up under real usage, not just demos. My work covers the full pipeline: retrieval architecture, agent design, voice integration, and cost optimization, so the LLM bill doesn't become a second project six months in. I don't just wire up an API to a model, I build systems that keep answering correctly and keep costing what they should, long after launch. My expertise includes: RAG Chatbots & Retrieval Architecture (Hybrid Search, Re-ranking, Semantic Caching) Autonomous AI Systems & Multi-Step Agent Workflows (LangGraph, Tool Calling, Memory) Voice AI Agents & Conversational IVR (Inbound Calls, Appointment Booking, Automated Follow-ups) LLM Cost Optimization (Query Compression, Token Budgeting, Sentence-Aware Chunking) Vector Databases & Semantic Search (Pinecone, pgvector, ChromaDB, FAISS) AI Workflow Automation & Custom Chatbots / Internal Knowledge Bases Full-Stack AI Applications (Python, FastAPI, n8n, Zapier) Cloud Deployment & Integration (AWS, Google Sheets/Calendar API, Docker) Recent projects include: Legal Document Intelligence Platform — Designed a RAG engine for plain-language Q&A over complex legal documents, plus a generation engine that drafts custody agreements, contracts, and divorce filings from structured input. Cut manual drafting time from hours to minutes. Shopify Live RAG Chatbot Pipeline — Built a crawler that continuously feeds live product data from a client's Shopify store into a RAG chatbot, giving customers accurate, real-time answers with zero manual updates. Voice AI Agent for a Salon (Vapi) — Built an inbound voice assistant that answers calls, books appointments directly into Google Sheets, and sends automated confirmation emails — full hands-off front desk automation. LeanRAG — Cost-Optimized RAG Architecture — Implemented four layered cost-optimization techniques (semantic caching, query compression, token budget enforcement, sentence-aware chunking) that cut LLM inference costs by 30–40% without losing answer quality. Karachi Air Quality Index Forecasting System — Built an end-to-end ML pipeline (data collection, preprocessing, model training, deployment) as a usable predictive tool for a non-technical team. What you can expect: Clean, maintainable, production-quality code with clear documentation Retrieval and voice systems tuned for accuracy, not just plausible-sounding answers Cost-aware architecture — token budgets and optimization built in from day one Clear communication and reliable post-deployment support I work with startups, growing businesses, and teams building AI products for measurable results, not experimental prototypes. If you're dealing with a support bottleneck, need a RAG chatbot that actually knows your documents, an autonomous system that runs a workflow end-to-end, or an LLM bill that's gotten out of hand, message me and I'll recommend the most practical approach.