Senior Site Reliability Engineer

Quick Facts

• Role: Senior Site Reliability Engineer (SRE) for production AI systems

Description

You will own the reliability, observability, and operational health of production AI systems, bridging deployment and long-term operability. The role focuses on embedding cost, security, and quality discipline throughout the solution lifecycle while driving automation and incident readiness.

Responsibilities

• Own deployment end-to-end using infrastructure as code, CI/CD pipelines, and environment management on Azure so every environment is rebuildable from source.

• Build LLM-aware observability with traces for every model call and production quality signals (eval sampling, drift detection, guardrail-trigger rates), plus cost and latency dashboards.

• Define and defend SLOs for availability, latency, and quality using data-driven error budgets to balance delivery speed and stability.

• Run incident management with on-call models, pre-written runbooks, and blameless postmortems.

• Manage the cost of intelligence by monitoring token economics, wiring budgets and alerts, and proactively planning capacity.

• Maintain security posture with patching, secret rotation, access reviews, and audit readiness across the lifecycle.

• Shape operability requirements before handover, ensure they are included in the definition of done, and run hypercare with sign-off on what will be operated.

• Feed operational patterns, failure modes, and cost learnings back to pods and the architect.

Requirements

• 5+ years of experience operating cloud production systems, including scaling, SLO definition, on-call operations, and automation.

• Expertise in Azure IaaS/PaaS operations, infrastructure as code (Terraform/Bicep), and CI/CD tooling.

• Proficiency with observability stacks, including LLM tracing, container orchestration, and Python/Bash automation.

• Knowledge of FinOps basics for AI workloads.

• Familiarity with daily AI-operations work: incident triage, runbook drafting, log analysis, and automation code.

Benefits

• Growth: career development programs, mentoring and well-being programs, certification support (Anthropic, Gemini, GCP, Azure, AWS), and English classes.

• Compensation and equity: stable pay and participation in an Employee Stock Purchase Plan with a 15% discount.

• Comprehensive benefits: health insurance, multisport, shopping vouchers, and referral bonuses up to $2,000.

• Work environment: hybrid by design with opportunities to work remotely within Poland; chance to work abroad up to 60 days annually; relocation opportunities; office amenities plus corporate, social, and well-being events.

• Note: benefits apply to employees; contractors are considered under individually agreed B2B terms.