Tool Calling Experiment
Experimental framework for enhancing LLM capabilities through dynamic tool integration, exploring function calling patterns, tool selection strategies, and error recovery mechanisms.
Sydney — |
PhD in Computer Science. I build machine learning systems that move from raw, messy data to decisions that hold up — in production, under pressure, at scale.
Most machine learning work looks clean in a notebook and breaks in production. I spent a PhD figuring out why — and the last four years at Prospa making sure it doesn't.
I'm a Data Scientist and ML Engineer based in Sydney. I build models that go into production, pipelines that don't fall apart when real data shows up, and dashboards that catch drift before anyone else notices.
Generative AI is where my head is right now — specifically what happens when LLMs meet messy, real-world business data.
I also write about this work. Not the polished version — the actual version.
Experimental framework for enhancing LLM capabilities through dynamic tool integration, exploring function calling patterns, tool selection strategies, and error recovery mechanisms.
A distributed multi-agent system where specialized AI agents collaborate, communicate, and coordinate to solve complex tasks that exceed the capabilities of individual agents.
A comprehensive analytics dashboard that integrates multiple machine learning models for real-time monitoring, performance comparison, ensemble predictions, and continuous learning across diverse data sources.
An intelligent learning analytics system that uses GraphRAG to track student learning journeys, identify knowledge gaps, and provide personalized recommendations based on concept relationships and learning pathways.
A graph-based Retrieval-Augmented Generation system that leverages knowledge graphs to enhance contextual understanding and improve LLM responses through structured relationship mapping.
A framework for discovering causal relationships from observational data and constructing causal graphs that enable counterfactual reasoning and intervention analysis for robust decision-making.
Designed and implemented an intelligent platform for automated assessment of learning outcomes. Features include adaptive testing, performance analytics, and personalized feedback systems.
Published in ACM Computing Surveys (2026), this comprehensive survey reconceptualizes explainability as a reflexive, system-level property spanning the entire ML lifecycle, introducing a cognitively grounded taxonomy and lifecycle-centric architecture for XAI.
Built a comprehensive framework for making machine learning models interpretable and transparent. Implemented various XAI techniques including SHAP, LIME, and feature importance analysis.
Developed an automated machine learning platform that streamlines the model development process. Features include automated feature engineering, hyperparameter optimization, and model selection algorithms.
Created a sophisticated stock market prediction system using time series analysis and deep learning models. Achieved 15% improvement in prediction accuracy compared to traditional methods.
Developed an NLP-based system that analyzes text to predict personality traits using machine learning algorithms. Processed large datasets and achieved 85% accuracy in personality classification.
Created an innovative virtual reality-based training simulator for medical ultrasound procedures. Combines computer vision and haptic feedback for realistic training experience.
Designed and deployed RAG-based and GraphRAG-based intelligent advising solutions, including chatbot, for courses and student progression, leveraging multi-agent LLM orchestration and knowledge graphs to deliver scalable, explainable, and policy-compliant decision support.
Built ML models, explainability frameworks, and production data pipelines, complemented by drift-monitoring dashboards to ensure performance stability and business impact.
Built and optimized a computer vision model for road sign detection and tracking, improving accuracy and real-time performance, and containerized the solution using Docker for scalable and reproducible deployment.
Designed and delivered undergraduate and postgraduate coursework in computer science and data science. Developed lab exercises that bridged theory and hands-on implementation, giving students practical experience with real tools and datasets.