Job summary
Mozn is hiring a Senior Site Reliability Engineer in Saudi Arabia to operate production systems and build LLM-based agents that automate repetitive SRE tasks. The role combines hands-on on-call incident work, application-level debugging, and designing safe, auditable agent workflows.
Key responsibilities
- Participate in on-call rotation and respond to incidents, investigate and remediate production issues.
- Debug application code, identify root causes and ship fixes directly to service repositories.
- Design, implement and deploy LLM-based agents that automate repetitive SRE workflows.
- Define agent tool interfaces, build safe wrappers and enforce least-privilege access.
- Set and enforce agent guardrails: approval gates, rollback paths, and audit trails.
- Develop evaluation and backtest suites to validate agent correctness and safety.
- Tune prompts, context and tool schemas as agents evolve.
- Report agent impact on MTTD/MTTR and engineer-hours saved.
Requirements
- 3+ years building production software with LLMs and agentic workflows.
- Hands-on experience with agentic coding tools like Claude Code or OpenAI Codex.
- Strong Python skills for tooling, API wrappers and orchestration.
- Real SRE experience as primary on-call responder and incident owner.
- Application-level debugging and ability to ship fixes into service repos.
- Hands-on Kubernetes and cloud provider experience and observability tooling.
- Understanding of guardrails: permissions, approval gates and rollback paths.
Benefits
- Competitive compensation
- Top-tier health insurance
- High responsibility and autonomy
- Work with leading AI talent in a dynamic environment
Skills
PythonKubernetesPrometheusGrafanaDatadogELKAWSGCPLLM agentsDocker
Source: Workable. Last checked as open: 14 Nov 2026. You apply directly with the employer.
Apply now
