Sannan A.

I'm an AI/ML engineer with 4 years of experience building computer vision, RAG chatbots, agentic AI, and workflow automation, along with the backend and deployment work that goes around them. I'm Top Rated on Upwork with a 100% Job Success Score. Most of my work falls into a few areas: RAG chatbots and agentic AI. I build assistants and automation on top of LangChain and LangGraph, using OpenAI and Claude models. This covers retrieval over your own documents, vector databases like Pinecone and ChromaDB, conversation memory, tool calling, and multi-agent setups. These usually need to talk to your existing APIs, databases, documents, or email and calendar, so I handle those integrations too. Workflow automation. I build automated workflows with n8n and OpenClaw to connect the tools a business already uses and cut out repetitive manual work. This includes things like routing incoming leads or emails, syncing data between apps, triggering actions from webhooks, and wiring AI models into those flows so a chatbot or detection result can kick off the next step automatically. If you're already running Zapier or Make and hitting their limits, n8n usually gives more control at lower cost. Computer vision. I train and deploy custom detection models with YOLO, PyTorch, and OpenCV. Past work includes PPE and safety monitoring, retail shelf and product analytics, and defect inspection, including real-time video, CCTV, and RTSP streams. I've also deployed to edge devices like the Jetson Nano. Python and machine learning. Data cleaning, EDA, feature engineering, and standard ML tasks (classification, regression, clustering), plus automation scripts and data pipelines with Pandas, NumPy, and scikit-learn. Backend and databases. REST APIs and model-serving endpoints in FastAPI and Flask, auth, third-party integrations, webhooks, and background jobs. I work with PostgreSQL, MySQL, Supabase, and vector databases, and I've built backends for React and Flutter apps. Deployment and MLOps. Docker, CI/CD with GitHub Actions or GitLab, model and dataset versioning, experiment tracking, AWS S3, and deploying to cloud VMs, with logging and monitoring once things are live. If you've got a project in mind, or a prototype that needs to be made production-ready, send me a message with some details and I'll let you know how I'd approach it and whether I'm a good fit.