Senior Site Reliability Engineer

About Mozn

Mozn is an Enterprise AI company focused on enabling organizations to make informed decisions in financial crime prevention and enterprise knowledge intelligence. The company fosters a diverse and collaborative environment, committed to building AI that delivers business value, builds trust, and empowers organizations through augmented intelligence. Mozn emphasizes excellence and meaningful impact in its culture.

The Role of Senior Site Reliability Engineer

Mozn is seeking a Senior Site Reliability Engineer with 3-5 years of experience to join its full-time team. This role involves a standard SRE workload, including on-call rotations, incident response, root cause analysis, and hands-on Kubernetes/cloud operations. A key aspect of this position is the development of agentic layers to automate repetitive reliability tasks over time. The Senior SRE will be responsible for identifying automation opportunities based on direct operational experience and building LLM-based agents to address them.

Key Responsibilities

• Participate in on-call rotations and act as a hands-on responder for incidents, including investigation, resolution, and documentation, particularly for workflows without existing automation.
• Address application-level reliability by debugging service code, understanding business logic to identify root causes, and implementing fixes directly within application repositories when appropriate.
• Design, build, and deploy LLM-based agents using tools such as Claude Code, OpenAI Codex, or Kimi K2/K3, integrating them with existing infrastructure including Kubernetes, cloud APIs, Prometheus/Grafana/ELK/Datadog, and PagerDuty/Slack.
• Define and build secure wrappers for the tool interfaces (APIs, scripts, read/write actions) required by each agent.
• Establish clear guardrails for agent autonomy, distinguishing between actions requiring human approval and those permitted autonomously, with an initial bias towards human-in-the-loop operation.
• Own agent evaluation by defining correctness and safety metrics and developing test/backtest suites against historical incident data.
• Continuously refine prompts, context, and tool schemas as agent scope expands.
• Collaborate with the SRE/platform team to identify suitable candidates for agent automation, focusing on repetitive, well-scoped, and auditable workflows.
• Report on agent impact, including improvements in MTTD/MTTR/MTTX, false positive/negative rates, and engineer-hours of toil removed.
• Maintain a security and compliance-first approach, ensuring audit trails for autonomous actions, least-privilege access to production, and adherence to Saudi data residency and regulatory requirements.

Desired Qualifications and Experience

• 3-5 years of experience in a relevant field.
• Experience with on-call rotations, incident response, root cause analysis, and Kubernetes/cloud operations.
• Proficiency in debugging service code and understanding business logic.
• Familiarity with LLM-based agent development and integration with existing tech stacks.

Preferred Attributes

• Experience in Saudi Arabia / MENA, particularly consulting for public or private sector clients.
• Familiarity with Terraform/Ansible, Docker, and VM/on-prem setups.
• Experience building evaluation and backtest harnesses for LLM agents using historical incident data.
• Background in ML engineering, LLMOps, or platform engineering.

Application Process

Candidates interested in this full-time Senior Site Reliability Engineer position at Mozn are encouraged to apply. Salary details will be discussed during the interview process.