DevOps with Gen AI Applications

We are seeking a highly experienced Senior DevOps Engineer with 10+ years of experience in DevOps, cloud infrastructure, automation, CI/CD, and container orchestration, along with hands-on experience supporting and deploying Generative AI applications., * Design, implement, and maintain scalable DevOps solutions for Generative AI and AI/ML applications.

• Build and manage CI/CD pipelines for application code, AI models, configuration, and infrastructure deployments.
• Automate infrastructure provisioning and configuration management using Terraform and Infrastructure as Code (IaC).
• Deploy, manage, and optimize containerized applications using Docker and Kubernetes.
• Manage cloud infrastructure and AI application deployments across AWS, Microsoft Azure, or Google Cloud Platform (Google Cloud Platform).
• Implement deployment automation for LLM-based applications, RAG pipelines, AI APIs, and model-serving services.
• Collaborate with AI engineers, ML engineers, data scientists, and application development teams to operationalize AI solutions.
• Implement MLOps/LLMOps practices for model deployment, versioning, testing, monitoring, and lifecycle management.
• Manage Git and GitHub repositories, branching strategies, pull requests, code reviews, and GitHub Actions workflows.
• Configure Kubernetes resources, Helm charts, autoscaling, ingress, secrets, and resource management for AI workloads.
• Implement monitoring, logging, alerting, and observability using tools such as Prometheus, Grafana, Datadog, or cloud-native monitoring services.
• Optimize cloud resource utilization, GPU infrastructure where applicable, application performance, and operational costs.
• Implement security best practices, including IAM, secrets management, network security, vulnerability scanning, and container image security.
• Troubleshoot production issues, perform root cause analysis, and improve system availability, reliability, and performance.
• Establish disaster recovery, backup, high availability, and operational support procedures.
• Develop automation scripts using Python, Bash, or PowerShell to streamline DevOps operations.
• Maintain technical documentation, deployment standards, runbooks, and operational procedures.

The ideal candidate will have strong expertise in cloud platforms, Kubernetes, Docker, Terraform, Git, GitHub, and CI/CD automation, with the ability to build scalable, secure, and reliable infrastructure for AI/ML workloads and LLM-powered applications. Experience implementing MLOps or LLMOps practices, automating AI application deployments, and managing production environments is highly desirable., * 10+ years of overall experience in DevOps, Cloud Engineering, Infrastructure Automation, or related roles.

• Strong hands-on experience designing and implementing CI/CD pipelines.
• Experience with Git, GitHub, GitHub Actions, Jenkins, GitLab CI/CD, or Azure DevOps.
• Proficiency in scripting and automation using Python, Bash, or PowerShell.

Cloud Platforms

• Strong experience with at least one major cloud platform: AWS, Microsoft Azure, or Google Cloud Platform.
• Experience managing cloud compute, networking, storage, identity, security, and monitoring services.
• Knowledge of cloud architecture, high availability, scalability, and cost optimization.

Containers and Kubernetes

• Hands-on experience with Docker, container image management, and container registries.
• Strong Kubernetes experience, including deployments, services, ingress, autoscaling, networking, and troubleshooting.
• Experience with Helm charts and Kubernetes configuration management.
• Understanding of container security and production-grade cluster operations.

Infrastructure as Code

• Strong experience with Terraform for provisioning and managing cloud infrastructure.
• Knowledge of Terraform modules, state management, reusable configurations, and environment management.
• Experience with Ansible or similar configuration management tools is desirable.

Generative AI and AI Application Operations

• Experience deploying, integrating, or operationally supporting Generative AI applications in cloud environments.
• Understanding of Large Language Models (LLMs), model-serving APIs, and AI application architectures.
• Familiarity with Retrieval-Augmented Generation (RAG), vector databases, embeddings, and AI application dependencies.
• Experience implementing CI/CD workflows for AI applications and, preferably, model artifacts.
• Knowledge of MLOps/LLMOps practices, including model versioning, deployment automation, evaluation workflows, and monitoring.
• Familiarity with AI services such as Azure OpenAI, Amazon Bedrock, or Google Vertex AI.
• Understanding of AI workload scalability, latency, availability, security, and cost management.

Monitoring, Security, and Reliability

• Experience with monitoring and observability tools such as Prometheus, Grafana, Datadog, Splunk, or cloud-native solutions.
• Knowledge of secrets management, IAM, vulnerability scanning, and secure deployment practices.
• Experience with incident management, root cause analysis, and production troubleshooting.

Preferred Qualifications

• Experience with GPU-enabled infrastructure or Kubernetes-based AI/ML workloads.
• Familiarity with MLflow, Kubeflow, KServe, or similar MLOps/model-serving technologies.
• Experience with Argo CD, FluxCD, or other GitOps deployment tools.
• Knowledge of service mesh technologies such as Istio.
• Experience with AI observability, LLM performance monitoring, and inference cost optimization.
• Exposure to enterprise AI security, data privacy, and responsible AI deployment practices., Bachelor’s degree in Computer Science, Information Technology, Engineering, or a related field, or equivalent practical experience., The ideal candidate will bring 10+ years of DevOps and cloud engineering experience, strong hands-on skills in Kubernetes, Docker, Terraform, GitHub, and CI/CD, and practical knowledge of deploying and operating Generative AI applications. The candidate should be comfortable working with AI/ML teams to build secure, scalable, automated, and production-ready AI platforms