Professional Overview
I'm a Backend / Applied AI Engineer with around 2 years of experience building AI-powered applications, specialising in Retrieval-Augmented Generation (RAG), document intelligence and LLM-based systems. I primarily work with Python, FastAPI, PostgreSQL, pgvector, BM25, vector search, Reciprocal Rank Fusion (RRF), cross-encoder reranking and AWS. I have experience integrating LLMs, building streaming APIs, developing document extraction pipelines using Docling, PyMuPDF and OCR, and improving retrieval quality and response performance. One of my key projects is a production-oriented RAG chatbot for educational content. I developed a multi-stage PDF processing pipeline, hybrid retrieval system and reranking workflow to improve the accuracy and relevance of answers. I also optimised intent routing, reducing measured routing latency from approximately 10 seconds to 300 milliseconds. I'm currently focused on advancing my expertise in Agentic AI, LangGraph, MCP, advanced RAG and LLM evaluation. I'm interested in building scalable, reliable AI solutions that solve real business problems for international teams.
Experience
Employment Type
Areas of Expertise
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.
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
