Architect, AI Platform
AI summary of the role
Red Hat seeks an Architect to design and scale its enterprise AI platform, bridging MLOps and AI with container-native infrastructure on OpenShift.
What you’ll do
- Architect and build production-grade MLOps pipelines on Red Hat OpenShift and OpenShift AI (RHOAI)
- Guide customers through model selection (Llama, Mistral, Granite) considering GPU, cost, and licensing
- Design containerized model deployment with KServe and inference servers (vLLM, TGI, Triton)
- Establish automated benchmarking pipelines for throughput, hardware efficiency, and cost-per-inference
What you’ll bring
- 8-10 years in related technology position (sales, consulting, operations, development)
- 5+ years with Public Cloud and Linux technologies
- 3+ years with Red Hat OpenShift Container Platform or Kubernetes
- 3+ years in production-ready AI solutions
Technologies
OpenShift · Kubernetes · MLOps · LLM · KServe · vLLM · TGI · Triton · RHOAI · Linux
About Red Hat
Sells enterprise subscriptions, support, and consulting for open-source infrastructure (RHEL, OpenShift, Ansible) and now open-source AI inference to large enterprises and the public sector.
Acquired · 5000+ people
Employer postings · Data from · Sources