DevOps Engineer

DevOps EngineerThe DevOps Engineer will own the deployment, scaling, and monitoring of GenAI systems across cloud-native and hybrid platforms. You'll collaborate with AI Engineers and infrastructure teams to ensure reliable and secure AI operations.Key Responsibilities:Design and manage CI/CD pipelines using GitHubDevelop and maintain robust CI/CD pipelines tailored specifically for deploying autonomous agentic AI systems and related software components.Build and automate cloud infrastructure optimized for deploying, scaling, and managing autonomous AI agents.Implement comprehensive monitoring, logging, and alerting for agentic AI processes, ensuring reliability, performance, and continuous improvement.Collaborate closely with Agentic AI engineers and architects to streamline workflows for training, deploying, and updating agentic AI models.Manage infrastructure security, access control, and compliance related to sensitive AI data and automated agent operations.Containerize and deploy LLM apps on hybrid infrastructure (e.g., public cloud, on-prem)Configure observability platforms such as Dynatrace for observability and incident responseAutomate integration and event-driven workflows using n8nSecure AI pipelines, manage secrets, and enable role-based access controlsCollaborate with QA for integration with test automation tools such as Functionize, Mabl, and PortRequirements:4+ years in DevOps, MLOps, or infrastructure engineeringExtensive experience with automation and infrastructure management supporting AI agent workloads.Expertise with containerization (Docker, Kubernetes), IaC (Terraform), and orchestration tools for agentic AI platforms.Familiarity with platforms and frameworks commonly used for autonomous AI agents (e.g., LangChain, LangGraph, Vector DBs, OpenAI APIs).Experience with GitHub Actions, container orchestration, MCP Servers, and hybrid cloud deploymentFamiliarity with Dynatrace for production monitoringExperience supporting LangChain, LangGraph, and vector databases (e.g., Qdrant)Strong security, scripting, and CI/CD automation backgroundDetail-oriented and proactive approach to system reliability, scalability, and security.Strong collaboration skills to efficiently support agile development cycles for agentic AI products.