What is your mission?

You will provide the best service to our partner brands by performing these tasks:

• Builds, operates, and maintains the AI platform environment as it transitions toward Kubernetes on OpenShift as the primary platform direction.
• Deploys and manages workloads on OpenShift supporting on‑prem AI clusters and customer‑facing AI infrastructure capabilities.
• Owns cluster reliability to ensure OpenShift‑based services are stable, production‑ready, and consistently available.
• Supports platform evolution, absorbs enhancements, and contributes to cloud‑native integrations built on OpenShift.
• Operates Kubernetes orchestration for AI services, ensuring workloads are properly deployed, scaled, and managed across the cluster.
• Maintains infrastructure layers that support AI inference workloads, with strong awareness of how the orchestration layer interacts with monitoring and other platform components.
• Participates in modernization work as the platform expands from current Linux operations into a full OpenShift/Kubernetes environment.
• Supports container delivery by managing Docker images, packaging deployable units, and ensuring containerized workloads meet AI infrastructure requirements.
• Provides expert-level operational support across Linux-based infrastructure, ensuring stability, predictable performance, and proper integration of services, drivers, and system dependencies.
• Handles essential components of AI stacks including NVIDIA GPU support, driver/kernel interactions, and hardware/software integration.
• Works with Git (GitHub/GitLab) through pull requests, commits, branching, and repository workflows as part of DevOps-driven infrastructure operations.
• Ensures infrastructure-as-code and automation changes are properly tracked, reviewable, and production-ready through source control.
• Utilizes tools such as Grafana and Prometheus for monitoring and observability.
• Supports environments involving ML frameworks, MLOps tools, and AI inference workloads (not model training or research).
• Applies familiarity with LLM orchestration tools (e.g., LangChain, LlamaIndex) and understands when simpler API-based approaches are appropriate.
• Contributes to environments using service mesh technologies such as Istio or Linkerd.
• Applies understanding of DevSecOps, security best practices, vulnerability scanning, API hardening (rate limiting, authentication middleware, input validation, security headers), and production WSGI servers such as Gunicorn or uWSGI.

Who are we looking for?

• Bachelor’s degree in Computer Science, Information Technology, Engineering, or a related technical discipline.
• Experience building, maintaining, and supporting infrastructure systems within OpenShift, Kubernetes, Linux, and Docker environments.
• Hands‑on experience supporting AI infrastructure, including hardware awareness (NVIDIA GPUs, drivers, kernels) and workload enablement for inference.
• Strong knowledge of OpenShift, including cluster operations, workload deployment, platform stability, and cloud‑native enhancements.
• Practical experience managing Kubernetes orchestration, scaling, production operations, and integration with monitoring services.
• Experience in container delivery, maintaining Docker-based deployment units, and ensuring operational readiness for AI components.
• Strong operational expertise in Linux, including system dependencies, services, performance tuning, and stability during modernization.
• Solid working knowledge of Git, including pull requests, commits, repository workflows, and collaborative DevOps practices.
• Familiarity with Grafana, Prometheus, and other observability tooling.
• Exposure to ML frameworks, MLOps tools, and AI infrastructure support (not model training responsibilities).
• Understanding of LLM orchestration tools, service mesh technologies, and security best practices for production APIs.
• Certifications in AWS, Azure, GCP, CKA, or CKAD are an advantage.
• Able to translate goals into AI‑assisted code generation, review generated code, and deploy it into production infrastructure.
• Strong technical communication skills, able to speak fluently about infrastructure layers, DevOps concepts, and repository/deployment workflows.