Senior AI DevOps Engineer AI Ops / Platform Engineering Hybrid - NTT DATA
Devops Engineer
We're looking for a Devops Engineer focused on streamlining processes and driving operational efficiency. This senior role requires 7+ years of relevant experience.
About the role
Design, build, and optimize AI-enabled CI/CD pipelines that improve developer productivity, deployment speed, and software quality.
Develop and deploy Model Context Protocol (MCP) clients and servers that securely connect enterprise LLMs with engineering tools, cloud infrastructure, and operational platforms.
Build custom MCP services using Python, TypeScript, JavaScript, or Node.js to expose infrastructure, deployment, monitoring, and operational data to authorized AI agents.
Integrate LLM-powered workflows for automated code reviews, testing, security analysis, release validation, and infrastructure recommendations.
Build and maintain enterprise CI/CD pipelines using GitHub Actions, GitLab CI, Jenkins, CircleCI, ArgoCD, or similar platforms.
Implement AI-driven ChatOps capabilities that enable engineers to interact with deployment pipelines, cloud environments, and operational tools through secure conversational interfaces.
Design intelligent remediation workflows for incident detection, root cause analysis, log analysis, and operational troubleshooting.
Develop secure Infrastructure-as-Code automation using Terraform, OpenTofu, Pulumi, Terragrunt, CloudFormation, or similar technologies.
Deploy and manage containerized applications using Kubernetes and Docker across AWS, Azure, or Google Cloud.
Build AI-powered observability solutions leveraging Datadog, Prometheus, Grafana, CloudWatch, Splunk, Dynatrace, ELK, or similar platforms.
Implement security guardrails including RBAC, least-privilege access, approval workflows, audit logging, rollback mechanisms, and secure AI tool access.
Partner with Engineering, Platform, Security, SRE, and AI teams to identify and implement intelligent automation opportunities.
Create reusable automation frameworks, documentation, dashboards, and engineering best practices that scale across the organization.
7+ years of experience in DevOps, Platform Engineering, Site Reliability Engineering (SRE), Cloud Engineering, or Infrastructure Automation.
4+ years designing and supporting enterprise CI/CD pipelines using GitHub Actions, GitLab CI, Jenkins, CircleCI, ArgoCD, or similar tools.
3+ years of cloud engineering experience in AWS, Azure, or Google Cloud (AWS preferred).
Strong experience deploying and managing Kubernetes and Docker in production environments (EKS, AKS, or GKE).
Hands-on experience with Infrastructure as Code using Terraform, OpenTofu, Pulumi, Terragrunt, CloudFormation, or similar tools.
Strong programming skills in Python, TypeScript, JavaScript, Bash, Go, or similar languages.
Experience integrating enterprise LLM platforms such as OpenAI, Anthropic, or equivalent AI services into engineering workflows.
Experience with AI orchestration frameworks such as LangChain, CrewAI, LlamaIndex, or similar technologies.