Abuse Reporting Automation Platform
End-to-end automation of trademark and abuse complaints across multiple platforms — FastAPI services, async workers and resilient browser automation.
role: Developer
What it does
Processes trademark and abuse complaints across multiple platforms, removing the manual submission workload from analysts.
Engineering
- FastAPI service layer + async worker engine
- Playwright/Selenium automation for submission, email verification and attachments — with retry, backoff and failure recovery for unreliable third-party portals
- Vision-LLM screenshot analysis and LoRA-tuned triage (see related projects)
- PostgreSQL, Azure Blob Storage and Key Vault, Redis — credentials and evidence encrypted at rest
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.