ZhenYuWang
I build LLM-powered systems that solve real business problems — from agentic workflows to retrieval-augmented generation and LLM evaluation infrastructure.
TALK TO MY AI TWIN
Explore my experience, projects, and what makes me different.
SHIPPED IN PRODUCTION
Healthcare Operations AI Agent
An AI agent for a hospital maternity ward that queries clinical and operational data across an 11-table database to automate bed scheduling, risk monitoring, and order management. Built on AWS Bedrock with Strands Agents and 7 registered tools (3 read-only for schema inspection and SQL querying, 4 write-operations with business logic validation), integrated with a Next.js chat interface via SSE streaming for real-time multi-turn dialogue.
Prompt Eval & Adversarial Testing
An LLM-as-Judge evaluation pipeline for an enterprise LLM system. Roughly 200 annotated test cases (25% of them adversarial) cover six use cases and are scored on business correctness plus five security risk dimensions. Wired into GitHub Actions CI with deployment gates and S3-persisted regression metrics, it became the team's first formal prompt QA process before production releases.
LET'S BUILD TOGETHER
I'm an MS CS candidate actively looking for internship / co-op roles in AI engineering. Shipped autonomous AI agents, LLM evaluation pipelines, and real-time inference systems on AWS, and ready to bring that energy to your team.