I build AI-powered applications, RAG systems and multi-agent workflows, and I secure them. My background includes building production software and security work; these two focuses taught me how systems are built, where they break, and best practices to secure them.
- 🤖 AI/LLM development: built an end-to-end RAG chatbot (Python, LangChain, MongoDB) for natural-language queries of environmental datasets on a production MERN-stack platform (NSF-funded Sustainability Hub)
- 🔬 Honors thesis: security of multi-agent LLM systems — built AETHER, an open-source framework for configuring multi-agent LLM systems with a YAML file, and AEGIS for testing how autonomous agents can be attacked when they coordinate, and which topologies hold up best
- 🌱 Currently preparing for Hack The Box's CPTS exam to deepen the offensive knowledge that sharpens both my testing and my building
Built AETHER (Agent Ecosystems for Testing, Hardening, Evaluation, and Research), an open-source framework for configuring early-stage multi-agent LLM systems using a declarative, human-readable file, and expanded it with AEGIS (Adversarial Evaluation and Guarding of Intelligent Systems) to facilitate one-shot attacks input either pre- or mid-execution.
- Declare a multi-agent system via YAML; interact through a Streamlit app
- Attack-testing suite covering five vectors: prompt injection, structured jailbreak, memory poisoning, bias inheritance, agent impersonation
- Empirical evaluation across attack dimensions and agent topologies, plus security guidelines for production multi-agent deployments
- Presented at MSU Denver's Honors Thesis Symposium; related research presented at the NAIRR Pilot Annual Meeting 2026 and MSU Denver's Undergraduate Research Conference
Contributed to an end-to-end RAG chatbot (Python, LangChain, MongoDB) that opens environmental datasets to researchers and policymakers through natural-language queries, on a production MERN-stack platform with secure, authenticated API endpoints.
AI / LLM Development
- AI/LLM Developer — RAG, agentic & multi-agent systems
- Applied AI / GenAI application development
Security
- Application Security
- AI / LLM Security & Red Teaming
- Detection Engineering & DFIR
