Senior AI SRE: Reliability, Observability & FinOps Hybrid

EPAM Systems; Warszawa; Hybrid; PLN 180,000 - 320,000; Full time

Benefits offered by this job

Hybrid by design

Remote work within Poland

Stock Purchase Plan

Health insurance

Alumni/relocation opportunities

Job summary

EPAM Systems is seeking a Senior Site Reliability Engineer to own reliability, observability, and operability of production AI systems. You will bridge deployment and long-term operability while embedding cost, security, and quality discipline into every solution's lifecycle.

You will lead end-to-end deployment on Azure, build LLm-aware observability, define SLOs, manage incidents, and maintain security posture across the lifecycle. Hybrid work options available in Poland.

Qualifications

• 5+ years building and operating cloud production systems with strong SRE fundamentals.
• Expertise in Azure IaaS/PaaS, IaC (Terraform/Bicep) and CI/CD tooling.
• Experience with observability stacks and LLM-aware tracing.
• Familiarity with FinOps basics for AI workloads and on-call automation.

Responsibilities

• Own deployment end-to-end with IaC, CI/CD, and environment mgmt on Azure.
• Build LLM-aware observability with traces, cost and latency dashboards.
• Define and defend SLOs for availability, latency, and quality.
• Run incident management including on-call, runbooks, and blameless postmortems.
• Manage AI costs via budgets, alerts, and capacity planning.
• Maintain security posture through patching, secret rotation, and access reviews.
• Shape operability requirements and handover with pods.

Skills

Azure IaaS/PaaS operations

CI/CD tooling

LLM tracing observability

Python/Bash automation

On-call automation

Tools

Terraform

Bicep

Kubernetes

Azure DevOps

Python scripting

Job description

EPAM Systems is seeking a Senior Site Reliability Engineer to own reliability, observability, and operability of production AI systems. You will bridge deployment and long-term operability while embedding cost, security, and quality discipline into every solution's lifecycle.

You will lead end-to-end deployment on Azure, build LLm-aware observability, define SLOs, manage incidents, and maintain security posture across the lifecycle. Hybrid work options available in Poland.