AI Engineer specializing in autonomous multi-agent architectures, LLM orchestration, and adversarial security tooling.
- Autonomous Agent Architectures: Multi-model reasoning loops, structured tool-calling pipelines, and Model Context Protocol (MCP) integrations.
- Offensive AI & Red Teaming: Automated reconnaissance workflows, exploit synthesis, and LLM adversarial evaluation (creator of Cybermes).
- Systems & Local Inference: High-concurrency Go & Python backends, containerized pipelines, and self-hosted model serving (Ollama, vLLM).