Overview
Seeking a Kubernetes Platform Engineer to support the production rollout of an existing enterprise Kubernetes environment and assist with AI gateway evaluations and deployments.
This resource will serve as a hands-on engineering contributor embedded within the customer environment, leveraging established platform designs and deployment manifests to complete production implementation efforts, troubleshoot issues, and support AI platform initiatives.
This is a highly technical, execution-focused role requiring strong Kubernetes, Linux, networking, storage, automation, and platform troubleshooting experience.
Primary Responsibilities
- Execute and validate production Kubernetes deployments using existing platform designs and deployment manifests
- Troubleshoot Linux, container, networking, storage, and cluster-related issues
- Deploy and support AI gateway proof-of-concepts and inference platform integrations
- Integrate and validate model-serving endpoints
- Evaluate authentication, routing, rate limiting, observability, and platform performance
- Support Kubernetes networking, ingress, load balancing, DNS, storage, and security configurations
- Maintain deployment automation workflows and operational runbooks
- Document findings and provide knowledge transfer to customer teams
- Collaborate with platform engineering teams to resolve infrastructure and application issues
- Provide recommendations related to platform performance, scalability, and operational readiness
Required Qualifications
- Proven experience deploying and supporting production Kubernetes environments
- Strong experience with on-premises or bare-metal Kubernetes deployments
- Advanced Linux administration experience
- Experience with container runtimes and containerized application deployments
- Strong knowledge of: Kubernetes Networking, DNS, Ingress Controllers, Load Balancing, Persistent Storage, RBAC, Secrets Management, TLS/Certificates
- Experience with Helm, Kustomize, YAML, and Git-based deployment workflows
- Python and/or Bash automation experience
- Experience with Prometheus, Grafana, or similar monitoring platforms
- Experience integrating APIs, AI services, or inference endpoints
- Ability to work independently within a customer environment
Preferred Qualifications
- NVIDIA GPU infrastructure experience
- GPU Operator implementation and support
- GPU monitoring and optimization
- vLLM or similar LLM-serving platforms
- AI/API Gateway products (Solo.io, Kong, Apigee, NGINX Gateway, etc.)
- RDMA, InfiniBand, or RoCEv2 experience
- NCCL performance testing
- Slurm workload scheduler experience
- Certified Kubernetes Administrator (CKA)
Rate:
Not specified
Location:
Remote
IR35 Status:
Not specified
Remote Status:
Remote
Industry:
IT
Seniority Level:
Senior