Senior DevOps Engineer (AI-Enabled Platform Engineering)
EverOps, Remote
What you will do
- Develop and use automation tools effectively to operate, manage, and scale production and development environments quickly
- Design and operate platform infrastructure that supports both traditional and AI/ML workloads—model serving endpoints, inference scaling, GPU-aware scheduling, and managed AI service integration
- Build AI-augmented operational tooling including agentic runbook execution, AI-assisted incident triage, and intelligent alerting pipelines
- Use AI coding tools (Claude Code, GitHub Copilot) as standard delivery accelerators across infrastructure and automation work
- Integrate managed AI services (AWS Bedrock, SageMaker, or equivalent) into client platform architectures, including vector store infrastructure and RAG-supporting patterns
- Automate toil reduction using LLM-powered automation—generating IaC, synthesizing operational insights, and accelerating documentation workflows
- Implement new tools and technologies as customer requirements evolve, with a focus on AI-readiness across the platform stack
- Monitor environments while focusing on constant improvement, including observability for AI workloads (inference latency, model endpoint health, token throughput)
- Support production workload migrations using blue-green and progressive delivery patterns
- Contribute to multi-tenant Kubernetes platform operations and maintenance
- Participate in regular customer and internal EverOps scrums
- Contribute to internal AI practice development, client AI readiness assessments, and the evolution of EverOps’ agentic engineering methodology
What you need
- 5+ years of professional experience as a DevOps, CloudOps, Platform, or Site Reliability Engineer
- Hands-on experience and deep understanding of Linux
- Strong hands-on professional experience with either Golang, Python, Ruby, Bash, Typescript, or Rust
- Strong hands-on experience with Amazon Web Services, Google Cloud, or Azure designing, building, and running highly-available cloud-native environments
- Production experience with Amazon EKS including multi-tenant cluster architecture, namespace isolation, and RBAC models
- Experience deploying or operating AI/ML infrastructure—model serving endpoints, inference APIs, GPU instances, or managed AI services (Bedrock, SageMaker, or equivalent)
- Familiarity with AI-assisted development workflows and agentic tooling (Claude Code, Copilot, or similar) as applied to infrastructure and automation work
- Understanding of vector databases, retrieval-augmented generation (RAG) patterns, or LLM integration at the infrastructure level
- Experience with ArgoCD for GitOps-driven deployments; federated ArgoCD experience a plus