LLM Security & Red-teaming

Breaking and hardening LLM systems: adversarial testing, prompt-injection and jailbreak research, guardrails, and Responsible-AI evaluation with LLM-as-judge.

All RAG & Retrieval4 Model Training & Fine-tuning4 Architecture & Systems4 AI Projects6 LLM Security & Red-teaming1

LLM Security & Red-teamingAI Projects

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.

200+

attack cases mapped to OWASP LLM Top 10

evasion / mutation techniques

PythonPlaywrightLLM-as-JudgeFastAPIYAML configs+1