Design production AI infrastructure with Kubernetes and GPU expertise at Insight Softmax, working remotely across Latin America and Canada business hours. Lead customer architecture engagements for inference platforms, gateways, and large-scale AI services.

As an AI Architect, you will serve as the senior technical voice for customers operating AI infrastructure. You will shape architectures for GPU clusters, LLM inference, AI gateways, and supporting services. The work spans discovery, reference architectures, recommendations, estimates, prototypes, and implementation review.

Key Responsibilities

Lead discovery and translate goals into AI platform architectures

Design Kubernetes and bare-metal inference serving platforms

Architect routing, quotas, observability, and multi-site failover

Define multi-tenant,



sovereign, hybrid, and air-gapped architectures

Review implementations and own technical outcome quality

Requirements

Eight years in infrastructure, platform, or machine learning engineering

Three years designing production AI or ML platforms at scale

Production LLM inference experience with performance tuning

Solid Kubernetes, Linux, GPU infrastructure, and networking knowledge

Deep knowledge of AWS, GCP, or Azure; AWS preferred

Apply your Kubernetes, GPU infrastructure, and LLM inference expertise to customer-focused AI architecture at Insight Softmax remotely.

📌 Senior AI Infrastructure Architect (Winnipeg)
🏢 Insight Softmax Consulting
📍 Winnipeg