Senior Site Reliability Engineer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior SRE operating production systems and building LLM agents for Mozn, an enterprise AI company. Automating incident response, reliability toil, and observability workflows with guardrails.
Responsibilities:
- Carry a normal on-call rotation and act as a hands-on incident responder
- Investigate, fix, and document production incidents
- Perform application-level debugging and identify root causes in service code and business logic
- Ship fixes or pull requests directly into application repositories when appropriate
- Design, build, and ship LLM-based agents integrated with Kubernetes, cloud APIs, observability, and incident-management tools
- Define agent tool interfaces and build safe wrappers for APIs, scripts, and read/write actions
- Establish autonomy guardrails and human-approval requirements for agents
- Own agent evaluations and build test/backtest suites using historical incidents
- Tune prompts, context, and tool schemas as agent scope expands
- Partner with the SRE/platform team to identify suitable automation workflows
- Report agent impact using MTTD, MTTR, MTTX, false-positive/negative rates, and engineer-hours of toil removed
- Maintain security- and compliance-first operations with audit trails, least-privilege production access, and Saudi data-residency/regulatory alignment
Requirements:
- 3+ years building production software with LLMs, including agentic workflows, tool/function calling, multi-step planning, or RAG
- Hands-on experience shipping work with Claude Code, OpenAI Codex, or Kimi K2/K3
- Strong Python or similar programming skills for agent tooling, API wrappers, and orchestration
- Hands-on SRE experience as a primary on-call responder, including incident response and root cause analysis
- Application-level debugging skills and ability to read service code, trace failures to underlying logic, and ship fixes
- Hands-on Kubernetes and cloud provider experience with AWS, GCP, OCI, or Azure
- Fluency with Prometheus, Grafana, Datadog, or ELK
- Understanding of autonomous-system guardrails, permissioning, approval gates, rollback paths, and auditability
- Ability to build trust with technical stakeholders
- Experience in Saudi Arabia/MENA, Terraform/Ansible, Docker, VM/on-prem setups, LLM agent evaluation, ML engineering, LLMOps, or platform engineering are nice to have
Benefits:
- Competitive compensation
- Top-tier health insurance
- Responsibility and trust
- Freedom and autonomy in decision-making
- Fun and dynamic workplace
- Opportunity to work alongside leading AI talent
- Inclusive and empowering culture
- Opportunity to work at the forefront of AI in the Middle East
Similar Jobs
Senior Site Reliability Engineer – Kubernetes
Senior SRE securing Kubernetes reliability for Software Mind’s ServiceNow AI platform. Managing observability, incident response, deployments, and Node.js/JVM production troubleshooting.
DevOps Engineer
DevOps Engineer building and supporting scalable AWS and Nutanix infrastructure for DysrupIT’s technology consulting clients. Automating deployments, monitoring platforms, and resolving incidents across enterprise environments.
Site Reliability Engineer
Site Reliability Engineer maintaining Kubernetes and cloud infrastructure for Arango’s contextual AI data platform. Automating operations, observability, CI/CD, and reliability for enterprise AI systems.
DevOps Engineer
DevOps Engineer administering applications, databases, containers, and Kubernetes clusters for DATAGROUP, a German IT services provider. Supporting customer cloud and container transformation while developing technical expertise.
DevOps Engineer
DevOps Engineer building scalable GCP infrastructure, CI/CD pipelines, and observability systems for Ambush’s engineering, design, strategy, and AI consultancy. Improving reliability, security, automation, and disaster recovery while mentoring engineers and traveling to Australia for 2–3 months.
DevOps Engineer
DevOps Engineer ensuring reliable, scalable infrastructure for DuoKey’s enterprise cloud encryption and key-management solutions. Automating deployments, monitoring services, and strengthening security across AWS, Azure, and GCP.
DevOps Engineer II
DevOps Engineer II maintaining cloud infrastructure for Level Data’s K-12 education software services. Building CI/CD, automation, observability, and secure production platforms across AWS, Azure, and datacenters.
Senior DevOps Engineer
Senior DevOps Engineer building secure, scalable cloud infrastructure for Level Data’s K-12 education software. Leading CI/CD, automation, observability, reliability, and DevSecOps across AWS, Azure, and datacenter environments.
Senior DevOps Engineer
Senior DevOps Engineer building secure, resilient cloud and datacenter infrastructure for Level Data’s K-12 education software. Leading CI/CD, automation, observability, reliability, security, and cost optimization across engineering environments.
DevOps Engineer II
DevOps Engineer II maintaining cloud infrastructure for Level Data’s K-12 education software. Building CI/CD pipelines, automation, observability, and secure multi-cloud operations.
Site Reliability Engineer
Site Reliability Engineer maintaining AWS and Kubernetes infrastructure for Empower, a financial services company. Improving production reliability, observability, scalability, and incident response.
IT Systems DevOps Engineer
DevOps Engineer building automation and internal systems solutions for Cologix, a North American network-neutral interconnection and hyperscale edge data center company. Supporting reliable deployments, production infrastructure, and operational workflows.
Azure DevOps Deployment Engineer
Azure DevOps deployment engineer supporting EU cybersecurity systems in Poland. Managing ASP.NET deployments, CI/CD pipelines, Azure environments, and enterprise system configuration for Frontex ICT.
Senior DevOps Engineer – Core DevOps
Senior DevOps Engineer automating distributed infrastructure for Five9, a cloud contact center software provider. Improving platform availability, scalability, observability, and efficiency across cloud environments.
Site Reliability Engineer – SRE
Site Reliability Engineer operating Kubernetes-based identity security services for Software Mind’s enterprise clients. Monitoring production, resolving incidents, improving CI/CD, automation, resilience, and observability.
South North Network SRE Expert – SME
SRE Expert automating EVPN/BGP infrastructure for Bitdeer’s AI cloud and Bitcoin mining operations. Owning multi-site data center fabrics, WAN, internet edge, and intent-driven network workflows.
Senior DevOps Engineer – Storage
Senior DevOps Engineer operating high-performance Kubernetes storage for Mirantis, a Kubernetes-native AI infrastructure company. Automating NFS, Linux, and air-gapped storage platforms for GPU workloads at scale.
Senior DevOps Engineer – AI Cloud
Senior DevOps Engineer building and operating AI cloud infrastructure for Bitdeer’s Bitcoin mining and AI computing platforms. Automating deployments, Kubernetes infrastructure, GPU workloads, reliability, and security.
GCP DevOps Engineer
GCP DevOps Engineer designing secure infrastructure, CI/CD, and Kubernetes platforms for Sonatype. Improving developer delivery, reliability, observability, and software supply-chain security.
Senior Backend DevOps Engineer
Senior Backend DevOps Engineer operating AWS containerized microservices for the VA’s JLV clinical data viewer. Building CI/CD, observability, security, and disaster recovery capabilities.