Infrastructure Architect – AI/GenAI Platforms - KM
About this role
Employer-provided description, formatted for easier reading.
We are seeking an experienced
Infrastructure Architect
to lead architecture and technical strategy for enterprise-scale
GenAI, Agentic AI, and AI platform infrastructure
.
Key Responsibilities
- Define architecture and technical direction for
GenAI/Agentic AI platforms, model serving, agent runtimes, AI governance, evaluation, guardrails, observability, and AI operations
.
- Design multi-cloud AI platforms across
OpenShift AI/RHOAI, GCP Vertex AI/Gemini, Azure AI Foundry, AWS Bedrock, Anthropic Claude, and OpenAI
.
- Lead
GPU strategy, NVIDIA SuperPOD architecture, capacity planning, multi-region resiliency, active-active architectures, HA, and cloud DR
.
- Drive scalable, secure, highly available
Tier-1 production platforms
and influence technology roadmaps across cross-functional teams.
Required Qualifications
- 10+ years
in software engineering, infrastructure, and architecture;
5+ years
designing large-scale cloud-native platforms.
- Strong expertise in
Kubernetes/OpenShift, distributed systems, cloud architecture, AI/ML platforms, API platforms, and data platforms
.
- Deep knowledge of
GenAI, RAG, Agentic AI, model serving, and MLOps
.
- Proven experience architecting
highly available, scalable, and resilient production systems
.