Production AI systems, agent architectures, and scalable LLM infrastructure.
I develop AI systems that combine retrieval-augmented generation, multi-agent reasoning, and scalable LLM inference to solve real-world problems. My work focuses on building intelligent platforms that integrate generative and agentic AI to optimise business processes, making advanced AI capabilities accessible to users without a technical background.
Featured above is PickSmart, an agentic AI product search platform that uses retrieval-augmented generation and LLM agents to analyse product reviews and generate personalised recommendations through a multi-agent reasoning architecture.
Multimodal Agent Architecture with Image Generation
View SystemAI Research Assistant System with RAG and Contextual Reasoning
View SystemEfficient Fine-Tuning Framework for Vision-Language Models
View System8-bit Post-Training Quantisation Pipeline
View SystemVision-Language Model Reasoning Optimisation with GRPO
View SystemScalable LLM Inference Pipeline on AWS SageMaker
View SystemSatellite Image Classification System for Wildfire Detection
View System2D-landing Control Architecture with Neural Networks
View SystemFeature-Driven Optimisation Framework for Syngas Production
View SystemMachine Translation System with Transformer Architecture
View System