Amir Kamel Rahimi, PhD

Audit bot — Phase 1

• Led the architecture and delivery of enterprise AI chatbot, combining Azure AI Search, vector retrieval, and metadata-driven ranking to enhance knowledge retrieval across internal systems

Audit bot — Phase 2

• Delivered a production RAG architecture using Pinecone and internal data pipelines to generate evidence-based chatbot responses aligned with legal and operational requirements

RAG evaluation

• Implemented a RAGAS evaluation suite (faithfulness, context precision, answer relevancy) to benchmark retrieval and generation quality across test cases on every release

ETL Pipeline

• Deployed a scalable in-house document ingestion and ETL workflows using Azure Document Intelligence and Python, improving unstructured data ingestion to the Azure Blob Storage

Document Classification

• Designed and deployed AI classification model to automatically categorise legal documents to enhance case-routing capability

Financial Analysis Dashboard

• Deployed Azure Cosmos DB knowledge graph to model client accident timelines, linking key employment and payslip events to strengthen case analysis and evidentiary review

Project "Smart Hub"

• Contributed to the Smart Hub project by leading QLD clinical data mapping into the OMOP standard data model (SQL)
• Supported the research and implementation of the native Gen AI model with GPT-2, trained by the OMOP standard data (PyTorch)
• Collaborated with stakeholders to identify data requirements and deliver tailored solutions
• Guided ethics and governance processes to facilitate data access for the implementation of advanced analytics in Smart Hub

Project "QChat"

• Implemented the Gen AI chatbot "QChat" for QLD Government (Azure OpenAI API, Node.js, Next.js and TypeScript)
• Successfully integrated guardrails for the safe and ethical use of AI for public servants
• Implemented monitoring algorithm using Azure Insight Telemetry for tracking resources usage

Project "Insight Engine"

• Gathered business requirements to develop a Gen AI solution aimed at guiding future strategic planning in QLD
• Designed and implemented a Proof of Concept (PoC) and full deployment of a Gen AI RAG-based application (LlamaIndex)
• Successfully implemented the AI solution using Microsoft Azure Function Apps, Azure Cognitive Search and Cosmos DB, ensuring scalable and efficient performance in line with future-focused strategic foresight
• Created knowledge graphs in NetworkX and applied clustering techniques (community detection) to create future strategic scenarios for QLD, contributing to both high-level foresight and actionable strategic directions

Project "Infection Prediction"

• Led the design, development, and validation of an XGBoost model to predict catheter-related infection risks, contributing to improved patient safety and proactive infection control (Scikit-Learn, Pandas and MLflow)
• Employed data preprocessing techniques, feature engineering, and hyperparameter tuning (Bayesian) to enhance model accuracy
• Deployed final ML model in AWS SageMaker AI

Project "QUIET" (Queensland Integrated Element Tracker)

• Developed .NET app to manage data governance, data dictionary, data view, data modelling, decision support and data catalogue of QLD Health Electronic Medical Records
• Developed database schema in Azure SQL Database
• Maintained version control of the source code using GitHub with other developers in the team
• Prepared and maintained detailed documentation throughout the development lifecycle, including user manuals, technical specifications, and release notes

Project "Genie Application"

• Full-stack developer on the Genie application in an Agile development environment
• Worked in agile development methodology for writing code, test units and code maintenance

Project "Legacy Data Migration to AWS"

• Lead data migration engineer, responsible for migrating legacy clinical data to Amazon Cloud
• Mentored junior developers, providing technical guidance and support on development best practices, code reviews, and quality assurance