Melbourne, Australia / Australian Permanent Resident
Senior ML Engineer · Data Scientist · PhD in Search & Recommendation Systems. I build production AI across the stack: search ranking, retrieval pipelines, content understanding, LLM-powered workflows, RAG, and agentic automation.
My background spans classical IR and ML — PhD-level research on personalised ranking and search, four years building search, recommendation, and content-understanding systems at Redbubble over 100 M+ user events — through to the modern AI layer: LLM orchestration, RAG, agentic workflows, evaluation engineering, and CI/CD-grade deployment.
I’m strongest where retrieval quality, ML system design, and data engineering matter together: search that has to be measurable, recommendations that have to survive a real catalog, and agents that have to work reliably across messy enterprise data.
My GitHub projects span applied ML and AI products, search and retrieval systems, agentic developer tooling, data science workflows, and human-facing AI applications. I separate original builds, collaborations, and research forks clearly.
Open Projects Dashboard → GitHub project summaryHealthcare AI · Contract Intelligence
Australian medical contract automation: scanned PDF extraction, OCR correction, structured clause/entity extraction, Medicare/PBS validation, and risk assessment.
Agentic Developer Tooling
Browser-based remote orchestration for single coding agents (Remote Agent Workbench) plus a multi-agent parallel control plane across isolated git worktrees (AgentForge) — covering the full range of AI coding-agent workflows.
AI Curriculum Design · Instructor
6-week progressive course project I designed and instructed (13 students): build a production AI booking assistant from Pydantic state and Redis through LangGraph agents, MCP tools, multi-agent routing, NeMo Guardrails, and RAGAS evaluation to a Docker + Render capstone.
Multimodal RAG
Visual retrieval pipeline: sample video frames → CLIP embeddings → ChromaDB → natural-language queries with timestamped evidence and multi-provider LLM answers.
RepositoryOperator Automation
Back-office sourcing tool: SQLite catalog ingestion, supplier/compliance metadata, operator feedback loop, bilingual product data, and Three.js 3D bin-packing visualisation.
RepositoryCreative AI Workflow
Nonlinear writing and prompt-orchestration workbench with branching story state, per-branch LLM prompt drawers, React Flow mind maps, and Obsidian Canvas export.
RepositoryAI Engineer on CWBot and TriageAgent. Architect stateful multi-turn LLM agents with LangGraph and MCP, design RAG workflows over enterprise knowledge bases, implement guardrails and evaluation pipelines, and own CI/CD and deployment standards for production AI services.
Contribute runtime and serving optimizations for LLM backends used by agentic systems, including work around model execution reliability, prompt/runtime control, and scalable inference behavior.
Built and owned search ranking, recommendation, content-classification, and moderation ML systems. Delivered vector-search improvements with Marqo and GCP Vertex AI MLOps pipelines, lifting CTR by 10% and add-to-cart by 0.5%. Designed feature pipelines and ML infrastructure over 100M+ user events and led GA4 analytics migration.
Worked on web search, data mining, and Autosub, a collaborative subtitle-generation system using speech-to-text APIs and automated processing pipelines.
PhD in Computer Science — Search & Recommendation Systems, RMIT University. B.Sc. in Computer Science, Harbin Institute of Technology.
VLDB Journal, DASFAA, ADC. Research focus: personalized ranking, preference adjustment, and continuous summarization.
ADC Best Student Paper Award, DASFAA Best Student Paper Runner Up, Google Code Jam Top 1000, ACM-ICPC Asia Regional Silver Medal.
Google Cloud Professional Data Engineer, Microsoft Azure AI Fundamentals, GCP data lake / warehouse modernization, deep learning and NLP specializations.
My strongest fit is where search, retrieval, and ML engineering meet production AI: meaningful evaluation metrics, large or noisy catalogs, data pipelines that need to be reliable, and systems that need to improve measurably over time — not just demo well once. PhD-trained in search and recommendation, hands-on in data science and MLOps, now building LLM-powered systems end-to-end.
Start a conversation