Justin Zhao

I build LLM systems, agentic workflows, and AI products for real users and operational settings.

I'm an AI Engineer with 3+ years of experience building production LLM systems, agentic orchestration frameworks, and applied AI research pipelines. My systems have scaled to over millions user interactions across three concurrent consumer AI products, and I build tools that let both technical and non-technical users deploy production-grade AI systems. My stack includes Python, PyTorch, FastAPI, React, and TypeScript, with LLM tooling spanning vLLM, Ollama, OpenRouter, LangGraph, and AutoGen. I deploy these systems on AWS, GCP, and Azure using Docker, Kubernetes, and Terraform. Day to day, I architect full-stack agentic systems end to end, including a drag-and-drop LLM workflow builder with a FastAPI and Celery backend and an agentic trading framework with switchable model providers and multi-agent review loops. I build robust agentic systems, applying systematic evaluation methodology, cross-validated benchmarking, and bias-aware metrics to production decisions. My background also keeps me current with AI methods as they emerge: I apply LoRA, GRPO, and RLHF fine-tuning and multi-agent orchestration in production, and I've published peer-reviewed benchmarks on LLM performance and bias. I translate this work across audiences, mentoring engineers, briefing leadership, and representing my work externally. I'm looking for challenging problems in distributed agentic systems, production AI infrastructure, and evaluation-driven AI at scale.