Summary
Tony Lee is a Staff Software Engineer with 12 years of experience specializing in ML inference infrastructure, cloud-native platforms, and distributed systems. He designs and operates GPU-serving solutions on Kubernetes, balancing latency, throughput, autoscaling, and cost with measurable experiments and tooling. His recent work includes building an AWS EKS inference lab using Terraform, Karpenter, vLLM, and Prometheus/Grafana to validate zero-idle serving and queue-aware scaling, and he has a track record of improving release stability and developer velocity through containerization and automation. Tony pairs hands-on engineering—shipping critical migrations and performance optimizations—with clear architectural leadership and mentorship across global teams. Based in Sacramento, he combines an electrical engineering background (UC San Diego, UIUC) with entrepreneurial instincts from a CTO co-founder role, and enjoys task automation and data visualization as outlets for solving engineering puzzles.
12 years of coding experience
8 years of employment as a software developer
University of California San Diego
B.S., Electrical Engineering, B.S., Electrical Engineering at University of Illinois Urbana-Champaign