Professional Overview
I build AI systems that make decisions and then act on them. Two halves, and I do both: AGENTIC AI & LLM SYSTEMS RAG pipelines over private company data. AI agents with tool calling that hit real APIs and complete multi-step workflows instead of just answering questions. Document intelligence that reads unstructured files and writes structured records into a database, with a human-in-the-loop review queue so nothing wrong gets written silently. Workflow automation that removes repetitive operational work: intake, routing, extraction, follow-up. COMPUTER VISION & REAL-TIME VIDEO Production video analytics running on live camera feeds: detection, multi-object tracking, re-identification, pose estimation. Optimised to 60+ FPS with TensorRT and ONNX across edge and cloud. Shipped across surveillance, retail loss prevention, workplace safety, sports analytics and traffic monitoring. The combination is the point. Plenty of engineers can wire up an LLM. Far fewer can also calibrate a camera, train a ReID model, or work out why a tracker keeps losing identities. When a problem has both a perception half and a reasoning half, that overlap is where I am most useful. What I actually own:
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.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
data science & analytics
Extract business insights from raw data using statistical modelling, predictive analytics, A/B testing, and interactive dashboards.
NLP & Prompt Engineering
Build natural language processing systems, fine-tune large language models, and craft reliable production prompts for AI-powered products.
