Senior DevOps Engineer📣 Job Ad

About the Role

Mirai is seeking a Senior DevOps Engineer to build and manage the infrastructure supporting its Generative AI products. This full-time role, based in Riyadh, will focus on developing robust pipelines, scalable platforms, and secure operational controls essential for AI workloads. The ideal candidate will have prior experience running similar demanding workloads, including those involving GPUs, model serving, and inference autoscaling.

Core Responsibilities

This position involves owning and maintaining critical infrastructure components. Key duties include:

• Writing and maintaining infrastructure as code to ensure reproducible, reviewable, and recoverable environments.
• Managing CI/CD pipelines for building, testing, scanning, and deploying applications, agents, and model-serving services.
• Operating container platforms (EKS, ECS, or Fargate) and associated deployment workflows, including GitOps practices.
• Establishing the runtime environment for AI workloads, encompassing GPU capacity, model serving solutions (*, vLLM, Triton, TGI), inference autoscaling, and associated gateways and caching.
• Configuring and managing API gateways, networking, load balancing, DNS, and certificates for secure service exposure.
• Overseeing secrets management, identity, and the implementation of least-privilege access across all environments.
• Managing production databases, including clustering, replication, failover, backups, and recovery.
• Integrating comprehensive monitoring solutions, covering token usage and GPU utilization, with clear alerting and service objectives.
• Leading reliability and security practices, including incident response, policy as code, vulnerability and container scanning, and cost management, particularly concerning GPU resources.

Required Qualifications and Experience

Candidates should possess the following qualifications:

• A minimum of 8 years of overall experience in DevOps, SRE, or infrastructure engineering.
• Hands-on experience supporting AI or ML workloads in a production environment.
• Proficiency in infrastructure as code using Terraform or OpenTofu, including module design and remote state management. Experience with HCP Terraform is a plus.
• Experience with configuration management tools like Ansible.
• Solid AWS experience across compute, networking (VPC, subnets, security groups, load balancers, Route 53), IAM, and storage services.
• Strong CI/CD skills with GitHub Actions, including reusable workflows and secure credential handling.
• Expertise in containers and orchestration, specifically Docker with Kubernetes (EKS preferred), Helm, and container registries like ECR.
• Experience with API gateways such as Kong or Amazon API Gateway, including authentication, rate limiting, and routing configurations.
• Database operations experience, including clustering and high availability, with platforms like RDS or Aurora, PostgreSQL, and caching solutions such as Redis or ElastiCache.
• Proficiency in secrets management using HashiCorp Vault, AWS Secrets Manager, or Parameter Store.
• Experience with observability tools including Prometheus, Grafana, CloudWatch, and OpenTelemetry, or equivalent solutions.
• Comfort working in Linux environments and scripting with Bash and Python.

Technical Environment

The role operates within a dynamic environment focused on cutting-edge AI technologies. The infrastructure is built on AWS, leveraging containerization with Kubernetes and robust CI/CD practices. The work directly supports the development and deployment of Generative AI products, requiring a deep understanding of AI-specific infrastructure demands.

Work Location and Type

This is a full-time position located in Riyadh.