site reliability engineer

EPAM develops enterprise software products, open source solutions, and accelerators, including solutions for production AI systems.

• Own end-to-end deployment, including infrastructure as code, CI/CD pipelines, and environment management on Azure;
• Build LLM-aware observability with model-call traces, production quality signals, drift detection, guardrail-trigger rates, and cost and latency dashboards;
• Define and defend SLOs for availability, latency, and quality objectives, balancing delivery speed against stability with data-driven error budgets;
• Run incident management, including on-call models, pre-incident runbooks, and blameless postmortems;
• Manage intelligence costs by monitoring token economics, configuring budgets and alerts, and conducting proactive capacity planning;
• Maintain the security posture through patching, secret rotation, access reviews, and audit readiness across the solution lifecycle;
• Shape operability requirements before handover and ensure their inclusion in the pod's definition of done;
• Run hypercare jointly and sign off on what will be operated;
• Feed operational patterns, failure modes, and cost learnings back to the pods and the Architect.

• 5+ Years of experience operating cloud production systems, including scaling, defining SLOs, managing on-call rotations, and automating manual work;
• Expertise in Azure IaaS/PaaS operations, infrastructure as code with Terraform/Bicep, and CI/CD tooling;
• Proficiency with observability stacks, LLM tracing, container orchestration, and Python/Bash automation;
• Knowledge of FinOps basics for AI workloads;
• Familiarity with daily AI use in operations, including incident triage, runbook drafting, log analysis, and automation code.

• No conditions specified