Sr Specialist System Engineering - DevOps Engineer — AI & Pipeline Automation

AT&T; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

AT&T in Bengaluru, India, is seeking an experienced DevOps engineer to design, build and maintain Azure DevOps CI/CD pipelines for 5G NF deployment from labs to production. You will develop AI-assisted automation to analyze failures, health metrics, and telemetry, and create MCP servers exposing internal tools through controlled automation interfaces.

Collaborate with client teams to architect scalable CI/CD patterns, build reusable YAML templates, and ensure secure, observable deployments on

Qualifications

• Expert-level Linux experience with Bash, Python, and/or PowerShell.
• Automation with scripting languages and Infrastructure as Code (e.g., Ansible).
• Hands-on containerizing, deploying, debugging, and maintaining applications.
• Expert ability to build ADO Pipelines from the ground up using YAML.
• Proficiency with az cli commands and ADO Repos/environment management.

Responsibilities

• Design, build, and maintain Azure DevOps CI/CD pipelines that support 5G NF deployment with repeatable, secure promotion workflows.
• Develop AI-assisted pipeline automation that analyzes build failures, deployment issues, pipeline health, and telemetry.
• Build and maintain MCP servers exposing Azure, Azure DevOps, Kubernetes, repository, and deployment capabilities.
• Create self-healing pipeline workflows with diagnostics, escalation paths, and remediation steps.
• Collaborate with client project teams to architect CI/CD solutions aligned with enterprise DevOps standards.
• Develop reusable YAML templates, pipeline components, scripts, and automation libraries for standardized delivery.
• Integrate pipelines with source control, artifact repositories, approvals, environment gates, testing frameworks, security checks, and release governance.
• Support Kubernetes-based deployments by troubleshooting failures, configuration issues, readiness, health, and environment-specific behavior.
• Implement observability for CI/CD systems: metrics, logs, dashboards, alerts, failure trend analysis, and continuous improvement.
• Apply secure DevOps practices for secrets handling, access control, policy enforcement, code reviews, vulnerability checks, and auditable release execution.
• Create AI-assisted root-cause analysis tools and knowledge workflows for engineering teams.
• Lead technical discussions, demos, and hands-on training to raise DevOps maturity and AI-enabled automation adoption.
• Document architecture, operating procedures, automation patterns, troubleshooting guides, and standards.
• Continuously evaluate emerging DevOps, GenAI, LLM, and MCP capabilities for improvements.

Skills

Linux

Scripting Bash/Python

CI/CD automation

Azure DevOps pipelines

Containerization

IaC (Ansible)

Kubectl & Helm

JSON & YAML

Azure DevOps Repos

Education

Bachelor's degree in CS/ET/IT or related field

Tools

Azure DevOps

AKS

Kubernetes

AKV/Key Vault

Azure CLI

kubectl

Helm

Ansible

MCP servers

Job description

Job Responsibilities

• Design, build, and maintain Azure DevOps CI/CD pipelines that support 5G NF application deployment from lab environments through production with repeatable, secure, and automated promotion workflows.




• Develop AI-assisted pipeline automation capabilities that use LLMs to analyze build failures, deployment issues, pipeline health, and operational telemetry.




• Build and maintain MCP servers and AI-callable tool integrations that expose Azure, Azure DevOps, Kubernetes, repository, and deployment capabilities through controlled automation interfaces.




• Create self-healing pipeline workflows that can detect common failure patterns, trigger approved remediation steps, and provide clear diagnostics, confidence levels, and escalation paths.




• Partner with client project teams to understand delivery requirements, architect CI/CD solutions, and implement automation patterns aligned with enterprise DevOps standards.




• Develop reusable YAML templates, pipeline components, scripts, and automation libraries that standardize CI/CD delivery across applications, environments, and teams.




• Integrate pipeline workflows with source control, artifact repositories, approvals, environment gates, testing frameworks, security checks, and release governance processes.




• Support Kubernetes-based deployments by troubleshooting deployment failures, configuration issues, container readiness, service health, and environment-specific pipeline behavior.




• Implement observability for CI/CD systems, including pipeline metrics, logs, dashboards, alerts, failure trend analysis, and continuous improvement feedback loops.




• Apply secure DevOps practices for secrets handling, access control, policy enforcement, code review, vulnerability checks, and audit-ready release execution.




• Create AI-assisted root-cause analysis tools and knowledge workflows that help engineering teams quickly identify probable causes and recommended next actions.




• Lead technical discussions, working sessions, demos, and hands-on training to improve DevOps maturity and enable client teams to adopt AI-enabled pipeline automation.




• Document architecture, operating procedures, automation patterns, troubleshooting guides, and standards to ensure consistent adoption and long-term maintainability.




• Continuously evaluate emerging DevOps, GenAI, LLM, and MCP capabilities and recommend practical enhancements that improve delivery speed, quality, reliability, and operational efficiency.

Job Qualifications / Required Qualifications

• Expert-level Linux experience with strong scripting skills in Bash, Python, and/or PowerShell




• Proven ability to automate manual processes using scripting languages and Infrastructure as Code (e.g., Ansible)




• Hands-on experience containerizing, deploying, debugging, and maintaining applications




• Expert ability to build ADO Pipelines from the ground up using YAML




• Proficiency with az cli commands within ADO Pipelines to interact with Azure Resources




• Deep understanding of ADO Repos including branching, tagging, and environment management strategies




• Working knowledge of ADO Agents – their purpose, capabilities, and limitations




• Strong use of JSON and YAML as data formats across scripts, Ansible playbooks, and pipelines

Azure Platform & Infrastructure

• Experience with Azure Container Registry (ACR) to import, tag, and extract images and charts within pipelines




• Understanding of Azure Resource Manager, Endpoints, and Service Principals




• Ability to build Azure Resources using Bicep and ARM Templates with emphasis on parameterization




• Familiarity with Azure Key Vault (AKV) and Hashi Corp Enterprise Vault (HCEV) for secrets management




• Experience with Azure Operator Service Manager (AOSM)

Kubernetes & Container Orchestration

• Hands-on experience deploying, managing, and debugging workloads on Kubernetes (AKS preferred)




• Proficiency with kubectl for inspecting pods, logs, events, and resource states during pipeline-triggered deployments




• Ability to diagnose and resolve common deployment failures including CrashLoopBackOff, image pull errors, resource quota issues, and failed health probes




• Experience integrating Kubernetes deployment steps into ADO Pipelines including rollout strategies, namespace management, and environment promotion




• Familiarity with Helm charts for packaging and deploying applications through pipelines




• Understanding of Kubernetes RBAC, service accounts, and their role in secure pipeline-based deployments

AI & LLM Integration

• Hands-on experience integrating Azure OpenAI or equivalent LLM APIs into automation workflows




• Ability to design prompts for pipeline analysis, failure summarization, and root-cause diagnosis




• Familiarity with agent-based AI patterns including tool/function calling and Retrieval-Augmented Generation (RAG)

Experience designing and building custom MCP servers to expose internal APIs and data as AI-callable tools

• Experience designing and building custom MCP servers to expose internal APIs and data as AI-callable tools

Pipeline Intelligence & Analysis

• Ability to leverage ADO REST APIs to surface pipeline health metrics, flaky tests, and failure patterns




• Experience building AI-assisted workflows for root-cause analysis against pipeline logs




• Capability to design self-healing pipeline logic - detect, diagnose, remediate, and re-trigger

Communication & Collaboration

• Demonstrated ability to articulate complex technical concepts, solutions, and standards to stakeholders across varying skill levels - through both presentations and discussions




• Collaborative approach to working across platform, security, and application engineering teams

Preferred Qualifications

• Minimum bachelor’s degree in Computer Science, Electronics and Communication, Engineering, Information Technology, or a related technical discipline.




• Demonstrated experience building enterprise-grade Azure DevOps pipeline automation using YAML, reusable templates, environment gates, approvals, and automated release promotion workflows.




• Hands‑on experience integrating AI or LLM capabilities into DevOps workflows for build failure analysis, pipeline summarization, root-cause diagnosis, and recommended remediation.




• Experience designing or operating MCP servers, AI-callable tools, function‑calling frameworks, or controlled automation interfaces that interact with Azure, ADO, repositories, Kubernetes, or internal APIs.




• Practical experience with self‑healing or intelligent automation that detects recurring failure patterns, triggers approved remediation actions, and provides diagnostics with clear escalation paths.




• Strong working knowledge of Kubernetes‑based application deployments, Helm charts, container registries, kubectl troubleshooting, rollout strategies, and secure service account/RBAC practices.




• Experience using Azure services such as Azure Container Registry, Azure Key Vault, Service Principals, ARM/Bicep templates, Azure CLI, and Azure Operator Service Manager within automated delivery pipelines.




• Familiarity with observability and pipeline intelligence practices, including pipeline health metrics, log analysis, flaky test detection, dashboards, alerts, and continuous improvement feedback loops.

Exposure to GenAI patterns

• Familiarity with GenAI patterns such as prompt engineering, Retrieval-Augmented Generation, tool/function calling, agentic workflows, and responsible use of AI guardrails in automation scenarios.




• Ability to lead technical working sessions, document standards and operating procedures, and train client or engineering teams on AI-enabled DevOps pipeline automation.

Nice to Have

• Experience with GitHub Copilot extensibility or custom AI agents.




• Familiarity with vector databases and Azure AI Search for embedding-based workflows.




• Prior work building AI-powered DevOps dashboards or reporting tools.




• Experience with Kubernetes-native observability tools such as Prometheus, Grafana, or Datadog.

Additional Job Information

• This is an offshore role that requires daily collaboration with U.S. stakeholders, including overlapping work hours to ensure effective partnership and meet business needs.

Weekly Hours: 40

Time Type: Regular

Location: IND:KA:Bangalore / Epip Area, Hoodi Village, Whitefield Rd - Eqp: Plot 111/112, Epip Area, Hoodi Village, Whitefield Road

AT&T will provide reasonable accommodations to qualified individuals with disabilities. AT&T is a fair chance employer and does not initiate a background check until an offer is made.