I'm currently a Senior AI Engineer at Zhanwei AI, an early-stage startup where I serve as founding engineer. I own the full product lifecycle from PRD to production — system design, architecture decisions, and hands-on development. My current focus is building an agentic platform from 0→1, defining multi-agent orchestration architecture and driving technology selection across LLM providers, frameworks, and infrastructure.

Before that, I was on the email security team at Trend Micro, where I independently developed 4 microservices for an automated analysis platform handling ~1,000 false-negative cases per day — covering root-cause analysis, LLM-powered report generation (Azure OpenAI), async remediation, and case management. It reduced a 5–7 person support team down to 1 handling escalations only.

Earlier in my career, I spent 2.5 years as a threat expert mining patterns from ~4B emails/day of global traffic — the hands-on experience with manual bottlenecks is what drove me to build automation. Before that, I was an AI engineer at WNC, developing anomaly detection and object detection models deployed on edge devices with K3s and Jetson Nano.