I'm a data scientist and operating model designer with a background in analytics, engineering, and consulting — currently working at the intersection of machine learning, decision support, and responsible data.

I’ve completed a Master of Data Analytics at QUT and worked across the education, defence, and consulting sectors. I enjoy working on end-to-end data projects, from cleaning and exploration through to modelling, dashboards, and deployment.

• Languages: Python, R, SQL
• Frameworks: scikit-learn, Dash, Plotly, TensorFlow, Tidyverse
• Focus Areas: Machine Learning, NLP, Geospatial, Accessibility, Public Sector Analytics

Building a layout-preserving, AI-assisted PDF converter that transforms complex academic material—including mathematical content, diagrams, and tables—into accessible formats for visually impaired students.
Tech Focus: layout-aware segmentation · math parsing · multimodal content structuring · modular agent-based workflows
Learning Focus: LangChain/OpenAI Agents · PDF layout modeling · Assistive UX pipelines · Math OCR and accessibility standards

Developing an AI-powered, voice-interactive version of Billy Big Mouth Bass using on-device TinyML and a cloud-optional voice synthesis pipeline. This project explores multimodal AI interface design, natural language control, and real-time audio response on low-power hardware.
Tech Focus: TinyML · Edge AI · Audio I/O · Embedded Python (Arduino)
Learning Focus: Speech-to-AI agent flows · Audio synthesis · Cloud/offline agent design · On-device performance constraints

Creating an open-source dashboard that maps school catchments, feeder networks, and educational outcomes across Australia. Designed for policymakers, parents, and planners to better understand geographic and demographic impacts on access and performance.
Tech Focus: Geospatial analytics · Dashboarding · Public data pipelines
Learning Focus: Interactive insight design · Streamlit/Dash · Data storytelling for public-sector decision support

I'm beginning to explore the intersection of AI, data security, and edge-device intelligence — with a long-term goal of contributing to responsible, privacy-preserving AI infrastructure.

Key areas of learning:

• Secure AI workflows and architecture
• Lightweight on-device inference (TinyML, edge AI)
• Multi-modal input (image, voice, video)
• Unified API design and enterprise security considerations
• Data compliance and safeguards for intelligent assistants

This aligns with a future interest in contributing to early-stage data products that serve regulated sectors like healthcare, defence, or finance.