Senior DevOps Engineer📣 إعلان

About Mirai and the Role

Mirai is seeking a Senior DevOps Engineer to join its team in Riyadh, Riyadh Province. This full-time role is critical for building and operating the infrastructure that supports the company's Generative AI products. The position involves developing robust pipelines for code deployment, managing platforms for services and models, and implementing stringent controls to ensure overall security and reliability. The ideal candidate will possess experience with the unique demands of AI workloads, including GPU management, model serving, inference autoscaling, and token cost optimization, and will be instrumental in establishing operational standards for a growing engineering team.

Core Responsibilities

• Write and maintain infrastructure as code to ensure environments are reproducible, reviewable, and quick to recover.
• Own the CI/CD processes, including pipelines for building, testing, scanning, and deploying applications, agents, and model-serving services.
• Manage the container platform (EKS, ECS, or Fargate) and associated deployment workflows, integrating GitOps where appropriate.
• Establish and maintain the runtime environment for AI workloads, encompassing GPU capacity, model serving solutions (*, vLLM, Triton, TGI), inference autoscaling, and front-end gateways and caching.
• Administer API gateways, networking components, load balancing, DNS, and certificates to ensure services are exposed securely and predictably.
• Manage secrets, identity, and implement least-privilege access across all operational environments.
• Operate production databases, including clustering, replication, failover, backups, and recovery procedures.
• Implement comprehensive monitoring for all systems, including token usage and GPU utilization, with clear alerting and defined service objectives.
• Lead and enforce reliability and security practices, including incident response, policy as code, vulnerability and container scanning, and cost discipline, particularly relevant for GPU-intensive operations.

Experience Requirements

• Eight or more years of experience in DevOps, Site Reliability Engineering (SRE), or general infrastructure engineering.
• Demonstrated hands-on experience supporting AI or Machine Learning (ML) workloads in a production environment.

Technical Qualifications

• Strong proficiency in infrastructure as code using Terraform or OpenTofu, including module design and remote state management. Experience with HCP Terraform is a plus.
• Expertise in configuration management with Ansible.
• Solid experience with AWS services across compute, networking (VPC, subnets, security groups, load balancers, Route 53), IAM, and storage.
• Strong CI/CD implementation skills with GitHub Actions, including reusable workflows and secure credential handling.
• Proficiency with containers and orchestration technologies: Docker with Kubernetes (EKS preferred), Helm, and container registries such as ECR.
• API gateway experience with Kong or Amazon API Gateway, covering authentication, rate limiting, and routing.
• Database operations experience, including clustering and high availability, with RDS or Aurora, PostgreSQL, and caching solutions like Redis or ElastiCache.
• Secrets management using HashiCorp Vault, AWS Secrets Manager, or Parameter Store.
• Observability implementation with Prometheus, Grafana, CloudWatch, and OpenTelemetry, or close equivalents.
• Comfortable working in Linux environments and scripting with Bash and Python.

Operational Standards and Work Environment

This full-time position is based in Riyadh, within the Riyadh Province. The role requires a commitment to establishing and upholding high operational standards that a growing team will rely on, particularly in the context of advanced Generative AI infrastructure.

Application Information

Interested candidates are invited to apply for this Senior DevOps Engineer position at Mirai.