Description

You own the infrastructure for AI and LLM products, covering compute, orchestration, RAG pipelines, CI/CD, observability, and security posture.

This role is on-site.

Responsibilities

• Manage production Kubernetes clusters, container lifecycles, and Helm chart templating.
• Provision and maintain GPU infrastructure (A100/H100) and vector databases for RAG pipelines.
• Build and secure CI/CD pipelines using GitHub Actions and Azure DevOps with GitOps practices.
• Drive security reviews, manage secrets in Azure Key Vault, and ensure InfoSec readiness.
• Own on-call rotations, resolve production incidents, and write post-mortems with SLA focus.

Required Skills

• 5-8+ years in platform, SRE, or infrastructure engineering.
• Expert in Kubernetes, Docker, and Helm.
• Advanced Terraform for Infrastructure as Code.
• Proficient in Azure DevOps, GitHub Actions, and ArgoCD.
• Strong experience with Azure Monitor, Datadog, and OpenTelemetry.
• Experience with LLM inference (Triton/NIM) and GPU provisioning.
• Background in AI/ML infrastructure, specifically RAG pipelines and vector stores.

Preferred Skills

• Experience with AWS and Pulumi.
• Familiarity with Azure API Management.

Key Skills

Education

Bachelor's degree