Professional Overview
Full-stack developer who shipped production apps for 7,000+ users and built an agentic chatbot for an internal team Phase 1 — The agentic "Help" agent (CRUD via natural language): I started by researching function/tool calling with OpenAI, then went deeper into the Model Context Protocol (MCP). As a proof of concept, I built an MCP server that could perform CRUD operations directly on our database and connected it to Claude Desktop to validate the approach. I evaluated frameworks — I began with LangChain and built an initial POC for session management, then discovered Google ADK, which fit our needs better. Working from the official Google ADK docs, I built the agent: I learned Python fundamentals, used FastAPI for the backend, and worked through ADK's hooks, artifacts, and session management. The result was a working agentic chatbot that performs CRUD operations on our system through natural language. Phase 2 — The RAG-powered "Q&A" agent: A new requirement came in for a Q&A assistant that understood our entire (config-heavy) system. I researched Retrieval-Augmented Generation from the ground up — mostly through technical articles and videos. I learned r
Areas of Expertise
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
