Loading...
28+ years building production systems — from bare metal Linux to GPU-accelerated AI inference. Founder of SolidRusT Networks. Co-founded TriNimbus (acquired by Rackspace). 550+ models on Hugging Face with 3.7M+ downloads.
Principal Cloud & AI Platform Architect with 28+ years building and operating production systems. I design, build, and own the platforms that take business initiatives from concept to production. Co-founded TriNimbus (acquired by Rackspace, 2018). Currently building SolidRusT Networks — a production AI inference platform on self-hosted Kubernetes serving multiple consumer applications.
Production GPU inference with vLLM, multi-agent orchestration, 550+ models on Hugging Face
12-node K8s cluster, GitOps with FluxCD, 12+ years on AWS, Terraform, production monitoring
Every PoC starts with git and CI/CD — teams inherit working patterns, not documentation
// About me in code
{
"name": "Shaun Prince",
"role": "Principal Cloud & AI Platform Architect",
"location": "Vancouver, Canada",
"company": "SolidRusT Networks",
"experience_years": 28,
"platform": [
"AI Inference (vLLM, GPU)",
"Kubernetes (12 nodes)",
"AWS (12+ years)",
"Multi-Agent Orchestration"
],
"huggingface_models": 550,
"model_downloads": "3.7M+",
"education": "Ph.D. Computer Science",
"languages": ["English", "French"]
}Founded and architected a production AI inference platform serving multiple consumer-facing applications.
Delivered full-stack applications and cloud infrastructure for diverse clients.
Automated infrastructure and deployment processes for enterprise clients.
Production AI inference platform with vLLM, LiteLLM, and Claude integration. Serves multiple consumer applications with automatic failover.
Multi-agent AI system with 234 council members across 11 categories. Features RAG, tool-enabled agents, and democratic deliberation.
AI-powered game assistant for Ashes of Creation. Features RAG-based knowledge retrieval and natural language interaction.
API key management, Stripe billing integration, and user authentication. GraphQL API with React console.
Real-time updates from my open source contributions
Fetching latest repositories from GitHub...
Deep dives into my most impactful projects
Production AI Inference at Scale
Building a cost-effective, high-availability AI inference platform for multiple consumer applications.
Kubernetes-based platform with vLLM, automatic failover to Claude, and unified API gateway.
Production-Grade GPU Cluster
Need for reliable, GPU-enabled infrastructure to run AI workloads with zero-downtime deployments.
12-node cluster with FluxCD GitOps, comprehensive monitoring, and NVMe-backed NFS storage.
Feedback from colleagues and collaborators
I'm always interested in hearing about new projects and opportunities