← all work
Predictive Forecasting for a Banking Client
Forecasting models and automated reconciliation for a leading Australian bank — better accuracy than baseline and 40% less manual effort.
role: BI Developer @ Genpact
40%
less manual effort
↑
forecast accuracy vs baseline
Work
- Predictive forecasting models that improved accuracy over the existing baseline and informed operational planning
- Python/SQL/VBA automation of reporting and reconciliation — 40% less manual effort, recurring errors eliminated
- Power BI and Tableau dashboards for real-time KPIs, adopted across finance and operations
- Large-scale SQL ETL under strict financial data-security and audit protocols
nearest neighbours
Tool-Selection LLM — LoRA Fine-tune on xLAM
Teaching a small LLM to pick the right tool/API for an agent — and say how confident it is. LoRA-tuned Qwen3.5-2B with Unsloth on xLAM function-calling data: 50.6% → 100% accuracy, ECE 0.220 → 0.002.
Agentic AI Chatbot Platform
Production multi-agent assistant for cybersecurity & case management — a router agent dispatching to five specialist agents across hybrid RAG, text-to-SQL and action execution, on self-hosted vLLM.
RedForge — AI Red-teaming & GenAI Eval Platform
Target-agnostic platform that attacks any LLM chatbot with 200+ OWASP-LLM-Top-10 test cases and an adversarial mutation engine. Built on personal time, adopted as a company product.