Senior DevOps / Site Reliability Expert

EPAM·Kazakhstan, Uzbekistan, Armenia, Georgia·Удалённо·2д. назад

We are looking for a Senior DevOps / Site Reliability Expert ready to own the reliability and operational maturity of a production AI platform.

You will be the engineering foundation that keeps agentic content workflows running at scale, ensuring services are observable, deployments are automated, and infrastructure is reproducible. Working closely with AI and full-stack engineers, you will shape how the team builds, ships, and operates, with particular focus on the reliability challenges unique to LLM workloads: cost, latency, and non-deterministic failure modes. This is a role for someone who takes pride in building systems that others depend on.

Responsibilities

Own the reliability, scalability, and performance of the platform's services running on Azure Container Apps and AWS ECS
Build and maintain CI/CD pipelines (GitHub Actions) for automated build, test, and deployment across multiple microservices, including Docker image management, registries, and deployment config
Implement and manage infrastructure as code (Terraform, Bicep, or ARM) across Azure and AWS
Set up and maintain observability — monitoring, alerting, logging, and dashboards (New Relic, Langfuse, CloudWatch)
Manage Azure Service Bus, Blob Storage, Key Vault, and Container Apps configurations
Ensure security best practices — secret management, image scanning, vulnerability remediation
Implement auto-scaling, load balancing, and cost optimisation for AI workloads
Support incident response and establish runbooks for production services
Collaborate with AI engineers to optimise LLM API usage, token costs, and latency

Requirements

3+ years of SRE, DevOps, or platform engineering experience
Hands-on expertise in Azure (Container Apps, Service Bus, Key Vault), as well as Blob Storage and Azure OpenAI resource management
Proficiency in infrastructure as code using Terraform, Bicep, or ARM templates
Background in CI/CD pipeline design and maintenance (GitHub Actions preferred)
Skills in Docker and container orchestration, with Kubernetes experience as a strong plus
Competency in monitoring and observability with New Relic or equivalent, including LLM observability as a plus
Understanding of security practices, including secret management, vulnerability scanning, and image hardening
Capability to script in Python or Bash for automation
Familiarity with AI development tools as a daily user (Cursor, Claude Code, Copilot)
Excellent command of written and spoken English (B2+ level)