Senior DevOps & Automation Engineer (OCI, Multi-Cloud & LLMOps/Agentic Focus)

Mandatory Qualifications

• Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a related discipline. 
• 5–8 years of professional experience in DevOps, Cloud Engineering, Platform Engineering, or Software Development. 
• Hands-on expertise with Oracle Cloud Infrastructure (OCI), including networking, IAM, Resource Manager, security services, and Landing Zone implementations. 
• Strong programming skills in Python (including asynchronous programming), Go and/or Java, Bash scripting, and REST API development. 
• Practical experience with Infrastructure as Code using Terraform, OpenTofu, Ansible, and infrastructure automation practices. 
• Experience deploying and managing containerized workloads using Docker, Kubernetes (OKE preferred), Helm, and cloud-native deployment patterns. 
• Experience implementing CI/CD and GitOps pipelines using Jenkins, GitLab CI, GitHub Actions, ArgoCD, or equivalent platforms. 
• Working knowledge of agentic AI frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or LlamaIndex, including tool calling, memory management, structured outputs, and workflow orchestration. 
• Experience with OCI Generative AI Services, vector databases, AI model deployment, or enterprise LLMOps practices. 
• Strong understanding of observability, monitoring, security, and operational excellence using OCI Cloud Guard, Vault, OCI Logging Analytics, LangSmith, Arize Phoenix, or similar platforms. 
• Excellent verbal and written English communication skills with the ability to collaborate across distributed teams and produce high-quality technical documentation. 

Good-to-Have Qualifications

• Experience implementing production-grade autonomous AI agents and multi-agent orchestration platforms. 
• Experience integrating OCI-hosted AI solutions with OpenAI, Azure OpenAI, AWS Bedrock, or other enterprise AI platforms. 
• Knowledge of service mesh technologies and hybrid or multi-cloud networking architectures. 
• Experience working in enterprise financial services, banking, or highly regulated industries.  
• Familiarity with secure software supply chains, DevSecOps, and policy-as-code frameworks. 
• Experience with AI evaluation, prompt lifecycle management, model governance, and tracing frameworks. 
• Exposure to Site Reliability Engineering (SRE) practices, chaos engineering, and platform resiliency. 

Preferred Certifications (Minimum Two Preferred)

Oracle Certifications

• Oracle Cloud Infrastructure Generative AI Professional 
• Oracle Cloud Infrastructure DevOps Professional 
• Oracle Cloud Infrastructure Architect Professional 
• Oracle Cloud Infrastructure Multicloud Architect Professional 

Industry Certifications

• Certified Kubernetes Administrator (CKA) 
• AWS Certified SysOps Administrator – Associate 
• AWS Certified Developer – Associate 
• Microsoft Azure Administrator or Azure AI certifications (preferred) 

Self-Assessment Questions

Before applying, consider the following:

1. Have you designed and managed enterprise-scale infrastructure on Oracle Cloud Infrastructure (OCI) using Infrastructure as Code and cloud-native best practices? 
2. Are you proficient in developing production automation using Python, Go, or Java and integrating these solutions into modern CI/CD and GitOps pipelines? 
3. Have you deployed, operated, or supported Kubernetes-based platforms and containerized applications across OCI or other cloud environments? 
4. Do you have practical experience with LLMOps, agentic AI frameworks (such as LangChain, LangGraph, CrewAI, AutoGen, or LlamaIndex), or enterprise AI deployment pipelines? 
5. Can you independently troubleshoot complex cloud infrastructure issues, implement self-healing automation, and collaborate effectively across geographically distributed engineering teams?

 

 

• Design, deploy, and manage secure, scalable OCI Landing Zones, networking, IAM policies, and infrastructure using Infrastructure as Code (Terraform, OpenTofu, and OCI Resource Manager). 
• Build, deploy, monitor, and optimize production environments supporting LLMOps platforms, multi-agent orchestration frameworks, and autonomous AI workloads. 
• Develop self-healing DevOps automation by integrating OCI Generative AI services and autonomous agents into CI/CD pipelines, incident response, rollback mechanisms, and operational workflows. 
• Develop clean, maintainable automation and platform engineering solutions using Python, Go, Java, Bash, and REST APIs to support cloud operations and AI-enabled workflows. 
• Design and maintain declarative GitOps and CI/CD pipelines using Jenkins, GitLab CI, GitHub Actions, ArgoCD, and related DevOps tooling to enable zero-downtime deployments. 
• Deploy, scale, and operate containerized applications and AI agent runtimes using Docker, Kubernetes (OKE, EKS, AKS), Helm, and service mesh technologies. 
• Enable secure multi-cloud interoperability by integrating OCI with AWS, Azure, and third-party AI services through FastConnect, Direct Connect, and secure networking architectures. 
• Implement comprehensive observability, logging, tracing, security monitoring, and governance using OCI Logging Analytics, Cloud Guard, Vault, LangSmith, Arize Phoenix, TruLens, and related monitoring platforms. 

Career Level - IC3