Infra Architect - AI Platform & GenAI Infrastructure

About the Role

Lead architecture and technical direction for:

• Enterprise GenAI Platform
• Agentic AI Platform
• Model Serving Infrastructure
• Prompt and Evaluation Frameworks
• AI Governance and Guardrails
• Agent Runtime Platforms
• Observability and AI Operations
• Multi-Cloud AI Platform

Responsibilities

Design and drive architecture across:

• OpenShift AI / RHOAI
• GCP Vertex AI
• Gemini Models
• Azure AI Foundry
• AWS Bedrock
• Anthropic Claude
• OpenAI
• Platform Scalability & Resiliency

Lead initiatives involving:

• Capacity planning
• GPU platform strategy
• NVIDIA Super POD architecture
• Multi-region resiliency
• Cloud DR strategy
• Active-active platform architectures
• High availability and disaster recovery

Qualifications

• 10+ years of software engineering, infrastructure and architecture experience.
• 5+ years designing large-scale cloud-native platforms.

Required Skills

Strong experience with:

• Kubernetes/OpenShift
• Distributed systems
• Cloud architectures
• AI/ML platforms
• API platforms
• Data platforms

Deep understanding of:

• Generative AI
• RAG architectures
• Agentic AI
• Model Serving
• MLOps
• Experience designing highly available Tier-1 production systems.