I design and build multi-agent systems that autonomously solve complex engineering problems — from novel harness architectures to production deployment at scale.
Purpose-built agent harnesses where specialized AI agents collaborate on complex tasks — with structured communication, shared memory, and human-in-the-loop governance at every stage.
Intelligent model selection that dynamically routes between cloud and local models based on task complexity, context requirements, and cost constraints — optimizing for both capability and efficiency.
Real-time monitoring, evaluation, and control systems for autonomous AI operations — tracking agent decisions, resource usage, and performance across multi-agent workflows.
Autonomous ingestion of system artifacts and data
AI-driven decomposition of complex interdependencies
Evaluation against operational and safety baselines
Actionable intelligence with full evidence lineage
A systematic methodology for deploying AI agents against complex engineering problems. Each phase is autonomous, auditable, and governed.
One person. One server. 6 domains. Built with Claude Code.
Currently exploring opportunities in agentic AI systems, AI safety, and applied AI research.
jhon.arango@IntrepidCyberSecEng.com
(667) 355-4069