Applied AI Systems · AWS Networking · Multimodal Agents
I build practical AI systems that connect models, infrastructure, human workflows, and proof loops. My current work is Sanshar: an event-driven swarm testbed for Discord, voice, vision, cloud, and local machines.
I combine cloud operations, network debugging, customer support, and hands-on AI prototyping. My work is strongest where systems need to be useful in the real world: observable, rate-limited, reversible, and grounded in source evidence.
A live multi-agent systems testbed spanning Discord, local Macs, AWS relay networking, source packets, proof artifacts, and peer roles such as Doctor, June, Sakshi, and Tara.
A policy layer for deciding when an AI system should observe, probe, summarize, ask, act, escalate, or hold. The goal is lower noise and better grounded autonomy.
AI product prototypes around chess reasoning, board-state interpretation, visual context, and model-assisted tutoring workflows.
VPC, Route 53, WAF, Shield, and Network Firewall support across customer troubleshooting, packet-level reasoning, and production constraints.
Hands-on hospital network operations in Colorado, balancing reliability, security, and user-facing urgency.
University of New Haven teaching support, applied networking, and self-directed AI systems development.
Open to applied AI, customer-facing systems architecture, and agentic tooling roles.