DevOps Engineer – Agentic Engineering

We are seeking a passionate and motivated DevOps Engineer with exposure to AI and Cloud Technologies to join our growing team. This role is ideal for professionals with 1+ years of experience in DevOps, Cloud Infrastructure, Platform Engineering, or Site Reliability Engineering (SRE) who are looking to expand their expertise in AI infrastructure, automation, and cloud-native technologies.

The successful candidate will build agentic AI solutions on Azure that boost efficiency for our team and for the development teams using our cloud infrastructure and deployment tools. You'll embed AI agents into our cloud runtime and CI/CD pipelines, with governance and human-in-the-loop oversight, to automate routine tasks and speed up provisioning and deployments.

Key Responsibilities

Agentic Engineering

• Identify AI use cases that boost efficiency and let us scale to more teams and partners without proportional effort.
• Pinpoint manual work that grows with every new team or partner, such as onboarding, provisioning, and support requests.
• Design and build AI agents for the selected use cases, from prototype to production.
• Embed agents into CI/CD pipelines, provisioning workflows, and the cloud runtime.
• Operate, monitor, and maintain agents in production.
• Enforce governance, guardrails, and human-in-the-loop approval for agent actions.
• Measure efficiency and scalability gains, and continuously improve agent quality, reliability, and cost.

Cloud Infrastructure & Platform Operations

• Design, deploy, and maintain cloud infrastructure on Azure or AWS.
• Operate Kubernetes and container platforms for application and AI workloads.
• Automate infrastructure provisioning with Infrastructure as Code (IaC).
• Build and maintain Helm charts for application deployments.
• Troubleshoot infrastructure, networking, and deployment issues.

DevOps & Automation

• Build and maintain CI/CD pipelines with Azure DevOps, GitHub Actions, or similar tools.
• Automate operational tasks with PowerShell and C#.
• Drive release management, deployment automation, and environment provisioning.
• Use AI-powered tools to increase operational efficiency.

AI & MLOps Support

• Deploy and monitor AI/ML applications and services.
• Maintain MLOps workflows with Azure ML, MLflow, or Kubeflow.
• Monitor performance of AI workloads and their infrastructure.

Monitoring & Reliability

• Implement monitoring and alerting with Prometheus, Grafana, ELK Stack, or cloud-native tools.
• Resolve incidents, run root cause analyses, and optimize performance.

Improve system reliability, scalability, and availability.

Required Technical Skills

Agentic Engineering

• Hands-on experience building AI agents with LLMs
• Familiarity with agent frameworks such as Semantic Kernel, AutoGen, or LangChain
• Experience integrating agents with tools, APIs, and knowledge sources (e.g., MCP, RAG)
• Understanding of AI governance, guardrails, and human-in-the-loop patterns
• Ability to evaluate and monitor agents for quality, reliability, and cost
• Ability to identify use cases where AI improves efficiency and scalability
• Exposure to Azure ML, Kubeflow, or MLflow.
• Understanding of AI-assisted operations (AIOps).

Cloud Platforms

• Hands-on experience with at least one cloud platform: Microsoft Azure (preferred), AWS or GCP.

Containers & Orchestration

• Docker
• Kubernetes (basic to intermediate)
• Helm, including building reusable charts for teams to use

Infrastructure as Code

• Terraform and/or ARM Templates / Bicep, including building reusable modules
• Ansible (basic knowledge)

Programming & Scripting

• Python, PowerShell, Bash, C#
• Experience automating workflows and building developer tools

CI/CD & Version Control

• Azure DevOps and/or GitHub Actions
• Git-based workflows

Monitoring & Logging

• Prometheus, Grafana, ELK Stack, Azure Monitor or similar tools

Operating systems

• Linux
• Windows

Preferred Qualifications

• Bachelor's degree in Computer Science, IT, Engineering, or a related field.
• 1+ years in DevOps, Cloud/Infrastructure Engineering, Platform Engineering, or SRE.
• Hands-on experience with Docker and Kubernetes.
• Solid understanding of CI/CD and deployment automation.
• Familiarity with Infrastructure as Code.
• Basic knowledge of AI/ML deployment and MLOps.
• Experience building and running AI agents or LLM-based solutions, ideally on Azure.
• Track record of identifying AI use cases that improve efficiency and scalability.
• Understanding of responsible AI, governance, and human-in-the-loop practices.
• Knowledge of cloud security and networking basics.
• Experience working in Agile teams.
• Azure, Azure AI, AWS, Kubernetes, or Terraform certifications are a plus.

Nice-to-Have Skills

• Knowledge of GitOps practices.
• Experience with container security and vulnerability management.
• Familiarity with distributed systems and microservices architectures.

Benefits

DevOps Engineer - Agentic Engineering

Location: Bengaluru, India

Experience: 2-5 Years

Position Summary

We are seeking a passionate and motivated DevOps Engineer with exposure to AI and Cloud Technologies to join our growing team. This role is ideal for professionals with 1+ years of experience in DevOps, Cloud Infrastructure, Platform Engineering, or Site Reliability Engineering (SRE) who are looking to expand their expertise in AI infrastructure, automation, and cloud-native technologies.

The successful candidate will build agentic AI solutions on Azure that boost efficiency for our team and for the development teams using our cloud infrastructure and deployment tools. You'll embed AI agents into our cloud runtime and CI/CD pipelines, with governance and human-in-the-loop oversight, to automate routine tasks and speed up provisioning and deployments.

Key Responsibilities

Agentic Engineering

• Identify AI use cases that boost efficiency and let us scale to more teams and partners without proportional effort.
• Pinpoint manual work that grows with every new team or partner, such as onboarding, provisioning, and support requests.
• Design and build AI agents for the selected use cases, from prototype to production.
• Embed agents into CI/CD pipelines, provisioning workflows, and the cloud runtime.
• Operate, monitor, and maintain agents in production.
• Enforce governance, guardrails, and human-in-the-loop approval for agent actions.
• Measure efficiency and scalability gains, and continuously improve agent quality, reliability, and cost.

Cloud Infrastructure & Platform Operations

• Design, deploy, and maintain cloud infrastructure on Azure or AWS.
• Operate Kubernetes and container platforms for application and AI workloads.
• Automate infrastructure provisioning with Infrastructure as Code (IaC).
• Build and maintain Helm charts for application deployments.
• Troubleshoot infrastructure, networking, and deployment issues.

DevOps & Automation

• Build and maintain CI/CD pipelines with Azure DevOps, GitHub Actions, or similar tools.
• Automate operational tasks with PowerShell and C#.
• Drive release management, deployment automation, and environment provisioning.
• Use AI-powered tools to increase operational efficiency.

AI & MLOps Support

• Deploy and monitor AI/ML applications and services.
• Maintain MLOps workflows with Azure ML, MLflow, or Kubeflow.
• Monitor performance of AI workloads and their infrastructure.

Monitoring & Reliability

• Implement monitoring and alerting with Prometheus, Grafana, ELK Stack, or cloud-native tools.
• Resolve incidents, run root cause analyses, and optimize performance.

Improve system reliability, scalability, and availability.

Required Technical Skills

Agentic Engineering

• Hands-on experience building AI agents with LLMs
• Familiarity with agent frameworks such as Semantic Kernel, AutoGen, or LangChain
• Experience integrating agents with tools, APIs, and knowledge sources (e.g., MCP, RAG)
• Understanding of AI governance, guardrails, and human-in-the-loop patterns
• Ability to evaluate and monitor agents for quality, reliability, and cost
• Ability to identify use cases where AI improves efficiency and scalability
• Exposure to Azure ML, Kubeflow, or MLflow.
• Understanding of AI-assisted operations (AIOps).

Cloud Platforms

• Hands-on experience with at least one cloud platform: Microsoft Azure (preferred), AWS or GCP.

Containers & Orchestration

• Docker
• Kubernetes (basic to intermediate)
• Helm, including building reusable charts for teams to use

Infrastructure as Code

• Terraform and/or ARM Templates / Bicep, including building reusable modules
• Ansible (basic knowledge)

Programming & Scripting

• Python, PowerShell, Bash, C#
• Experience automating workflows and building developer tools

CI/CD & Version Control

• Azure DevOps and/or GitHub Actions
• Git-based workflows

Monitoring & Logging

• Prometheus, Grafana, ELK Stack, Azure Monitor or similar tools

Operating systems

• Linux
• Windows

Preferred Qualifications

• Bachelor's degree in Computer Science, IT, Engineering, or a related field.
• 1+ years in DevOps, Cloud/Infrastructure Engineering, Platform Engineering, or SRE.
• Hands-on experience with Docker and Kubernetes.
• Solid understanding of CI/CD and deployment automation.
• Familiarity with Infrastructure as Code.
• Basic knowledge of AI/ML deployment and MLOps.
• Experience building and running AI agents or LLM-based solutions, ideally on Azure.
• Track record of identifying AI use cases that improve efficiency and scalability.
• Understanding of responsible AI, governance, and human-in-the-loop practices.
• Knowledge of cloud security and networking basics.
• Experience working in Agile teams.
• Azure, Azure AI, AWS, Kubernetes, or Terraform certifications are a plus.

Nice-to-Have Skills

• Knowledge of GitOps practices.
• Experience with container security and vulnerability management.
• Familiarity with distributed systems and microservices architectures.