AI Architect and AI Engineer in Sydney, Australia. I design and build AI systems end to end, from models and retrieval to agents, evaluation and infrastructure: LLM applications, RAG and knowledge graphs, multi-agent workflows, and the harnesses around them. I'm also a doctoral researcher at Western Sydney University working on small object detection in fast-moving video.
Open source. I build open-source tools for AI-assisted development and AI systems (pinned below), and contribute to projects I use: code merged into LightRAG and RAG-Anything, and fixes to the FastMCP and Google ADK docs.
Research. Mitigating Roadkill Using Computer Vision and Machine Learning Techniques, IEEE ABC 2025.
Stack. Python, TypeScript, Rust, SQL 路 Google ADK, Pydantic AI, LangChain, LlamaIndex, MCP 路 LightRAG, Neo4j, Qdrant, pgvector 路 PyTorch, YOLO 路 Google Cloud, AWS, Azure, Docker, Terraform