Job Summary
The Senior AI Ops / DevOps Engineer will architect, build, and manage AI-driven CI/CD pipelines and cloud operations ecosystems. The role focuses on integrating LLM agents, Model Context Protocol (MCP) clients and servers, intelligent observability, and secure AI-assisted workflows into the software delivery lifecycle to improve developer productivity, code quality, release reliability, deployment speed, and operational efficiency while maintaining strong governance, security, and reliability.
Key Responsibilities
• Architect, build, and manage AI-enabled CI/CD pipelines to improve developer productivity, code quality, release reliability, and deployment speed.
• Design and deploy production-grade Model Context Protocol (MCP) clients and servers to securely connect enterprise LLMs with engineering tools, repositories, cloud infrastructure, and observability platforms.
• Develop custom MCP servers using Python, TypeScript, Node.js, or JavaScript to expose logs, infrastructure metrics, deployment data, and internal tools to authorized AI agents.
• Integrate LLM agents into developer workflows to support automated code reviews, vulnerability detection, test generation, release validation, and infrastructure recommendations.
• Build and maintain CI/CD pipelines using GitHub Actions, GitLab CI, CircleCI, ArgoCD, Jenkins, or similar tools.
• Implement ChatOps 2.0 capabilities that enable engineers to interact with deployment pipelines, cloud environments, logs, and operational workflows through secure conversational interfaces.
• Develop safe autonomous remediation workflows for log analysis, incident triage, root-cause analysis, and infrastructure issue resolution.
• Establish guardrails for AI agents to generate, inspect, and safely execute Infrastructure as Code using Terraform, OpenTofu, Terragrunt, Pulumi, Crossplane, or similar tools.
• Manage containerized workloads using Docker and Kubernetes platforms, including AWS EKS, Azure AKS, and Google GKE.
• Integrate AI-driven observability workflows with platforms such as Datadog, Prometheus, Grafana, CloudWatch, Splunk, Dynatrace, or ELK.
• Implement AI safety controls, including role-based access control, least-privilege execution, human-in-the-loop approvals, audit logging, rollback mechanisms, and secure tool access.
• Collaborate with software engineering, DevOps, SRE, security, platform, and data/AI teams to identify opportunities for intelligent automation.
• Develop reusable automation frameworks, runbooks, dashboards, documentation, and enablement materials for engineering teams.
• Promote an automation-first culture by reducing manual toil and improving operational efficiency across cloud and software delivery processes.
Required Qualifications
• Minimum 7+ years of experience in DevOps, Cloud Engineering, Site Reliability Engineering (SRE), Platform Engineering, or Infrastructure Automation.
• Minimum 4+ years of hands-on experience designing and managing CI/CD pipelines using GitHub Actions, GitLab CI, CircleCI, Jenkins, ArgoCD, or similar platforms.
• Minimum 3+ years of experience managing scalable cloud environments in AWS, Azure, or GCP, with a strong preference for AWS.
• Strong hands-on experience with Kubernetes, Docker, and production container orchestration platforms such as EKS, AKS, or GKE.
• Advanced proficiency in Infrastructure as Code tools such as Terraform, OpenTofu, Terragrunt, Pulumi, CloudFormation, or Crossplane.
• Strong programming and scripting skills using Python, TypeScript, JavaScript, Bash, or Go.
• Practical experience working with LLM APIs, including OpenAI, Anthropic, or similar enterprise AI platforms.
• Experience with AI orchestration or agentic frameworks such as LangChain, CrewAI, LlamaIndex, or similar tools.
• Strong understanding of the Model Context Protocol (MCP) ecosystem and experience designing or integrating MCP clients and servers.
• Experience integrating DevSecOps controls into CI/CD pipelines, including SAST, DAST, dependency scanning, container scanning, secrets scanning, and vulnerability management.
• Strong knowledge of secrets management and security tools such as HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, or similar platforms.
• Experience with observability, monitoring, logging, and alerting platforms such as Datadog, Prometheus, Grafana, CloudWatch, Splunk, Dynatrace, or ELK.
• Familiarity with security and compliance frameworks such as SOC 2, ISO 27001, or enterprise audit control environments.
• Ability to troubleshoot complex pipeline, infrastructure, deployment, and production issues across cloud-native environments.
• Bachelor's degree in Computer Science, Engineering, Information Technology, or equivalent work experience.
• Ability to work in the office 3 days per week, as required by the client/project.
Preferred Qualifications
• Experience building AI-assisted infrastructure provisioning workflows.
• Experience implementing autonomous or semi-autonomous incident response and remediation capabilities.
• Experience with MLOps, model deployment pipelines, model monitoring, MLflow, SageMaker, or equivalent platforms.
• Experience implementing human-in-the-loop approval models for AI-generated operational actions.
• Experience with policy-as-code tools such as Open Policy Agent, Sentinel, Checkov, or similar solutions.
• Experience working in regulated industries such as banking, financial services, healthcare, or insurance.
• Experience with GitOps operating models using ArgoCD, Flux, or similar tools.
• AWS, Kubernetes, DevOps, Security, or AI/ML certifications are a plus.
Soft Skills & Mindset
• Strong automation-first mindset with a passion for reducing repetitive manual tasks and operational toil.
• Security-first approach, with a focus on validating AI actions and implementing appropriate boundaries, approvals, and rollback mechanisms.
• Ability to collaborate across software engineering, DevOps, SRE, security, and data/AI teams.
• Strong communication skills, with the ability to explain complex AI-enabled DevOps concepts to technical teams and leadership.
• Ability to educate and upskill engineering teams on AI-assisted delivery, secure automation, and modern DevOps practices.
• Ownership mindset, with the ability to design solutions, implement them hands-on, and support them in production.
