Principal AI Infrastructure Platform Architect

TSMC; Vancouver (WA); On-site; USD 166,800 - 241,800; Full time

Job summary

TSMC Washington, LLC is seeking an experienced AI Infrastructure Tech Leader to define and build enterprise AI infrastructure for secure, scalable AI services. You will lead architecture for an enterprise AI platform, including model serving, governance, and AI gateways, collaborating with teams across North America and Taiwan to deploy AI capabilities at scale.

This on-site role in Vancouver, WA requires deep expertise in distributed systems, Kubernetes, GPUs, and cloud-native tooling.

Qualifications

• BS/MS/PhD in Computer Science or related field.
• 12+ years of software engineering experience.
• 5+ years leading architecture for distributed systems or cloud infrastructure.
• 3+ years hands-on experience designing enterprise AI platforms.
• 3+ years’ experience as a Principal Engineer, Staff Engineer, Distinguished Engineer, or Technical Lead.
• Strong technical communication skills for collaborating with global cross-functional teams.
• Experience with AI Infrastructure technologies including LLM inference, gateway, and AI serving infrastructure.

Responsibilities

• Define AI Platform Architecture and lead technical strategy for enterprise AI infrastructure.
• Build scalable AI infrastructure supporting LLM serving, GPU scheduling, model routing, and governance.
• Design distributed systems for high availability, multi-region deployment, and disaster recovery.
• Drive engineering best practices for Kubernetes, Platform-as-a-Service, and AI deployment automation.
• Provide technical leadership, mentor senior engineers, and align roadmaps across regions.

Skills

Distributed systems

Technical leadership

Communication

Go/Python/Java

Education

BS/MS/PhD in Computer Science or related field

Tools

NVIDIA GPU ecosystem

vLLM

TensorRT-LLM

Triton Inference Server

Ray

Kubeflow

MLflow

Kubernetes

Docker

Helm

ArgoCD

Service Mesh

AWS/Azure/GCP

Job description

TSMC Washington, LLC is seeking an experienced AI Infrastructure Tech Leader to define and build enterprise AI infrastructure for secure, scalable AI services. You will lead architecture for an enterprise AI platform, including model serving, governance, and AI gateways, collaborating with teams across North America and Taiwan to deploy AI capabilities at scale.

This on-site role in Vancouver, WA requires deep expertise in distributed systems, Kubernetes, GPUs, and cloud-native tooling.