Projects & Systems
Production LLM systems, retrieval pipelines, fine-tuning, architecture and AI security — filter by area below.
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.
DocuMind AI — Grounded Multimodal Document Q&A at Scale
System design for a 1M-user document Q&A product: async multimodal ingestion, hybrid retrieval, a deterministic confidence gate that refuses instead of hallucinating, and hot/warm/cold session tiering.
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.
3B Tokens/Day Vision-LLM Inference on One GPU
Scaled self-hosted vision-LLM screenshot analysis to 3 billion input and 50 million output tokens per day on a single 96GB GPU — no third-party API spend.
Self-learning Few-shot Text-to-SQL
A retrieval-driven few-shot engine that harvests successful queries as exemplars and injects them dynamically — lifting text-to-SQL accuracy from 60% to 95% with no retraining.
Hybrid RAG Retrieval Pipeline
BM25 + dense semantic search with cross-encoder reranking, per-document-type chunking and metadata filtering over a 200+ document enterprise knowledge base.
Vision-LLM LoRA Fine-tuning for Threat Triage
Fine-tuned a vision-language model with LoRA/PEFT to predict threat category directly from evidence screenshots, automating analyst triage.
Abuse Reporting Automation Platform
End-to-end automation of trademark and abuse complaints across multiple platforms — FastAPI services, async workers and resilient browser automation.
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.