Senior SRE Engineer (MLOps)📣 Job Ad

About the Role

Salla is seeking a Senior SRE Engineer (MLOps) to join the Salla AI team. This full-time position, based in Makkah, Makkah Province, focuses on operating AI and ML systems as production-grade services. The role is centered on the operational layer for models, prompts, agents, inference services, and retrieval systems, ensuring Agentic AI and Generative AI features function reliably, securely, and cost-effectively at scale within Salla's ecosystem.

Role Context and Focus

This is a platform-engineering-first SRE role with a strong emphasis on reliability, observability, safe release processes, cost management, and governance. The engineer will collaborate with engineering, data, and AI teams to facilitate a streamlined and secure path to production for AI-driven features. The role acknowledges that AI systems present unique operational challenges, such as prompt changes behaving like code modifications, the need for auditability in agent tool-calling, and the complex interplay of latency, quality, and cost.

Key Responsibilities

• Own production reliability for ML and agentic AI services, including SLOs, dashboards, alerts, runbooks, and incident follow-ups.
• Develop comprehensive observability across the AI stack, covering latency, errors, traces, tool calls, cost, and user impact.
• Design and implement safe release patterns for models, prompts, agents, tools, and configurations, utilizing strategies such as canary releases, rollbacks, feature flags, and evaluation gates.
• Provide operational support for inference APIs, queues, retrieval layers, and AI workflows running on Kubernetes/EKS.
• Establish ownership, traceability, and guardrails for agentic system actions, including their interactions with internal tools.
• Defend agent tool-calling mechanisms against prompt injection and untrusted data risks by enforcing data-trust boundaries.
• Drive AI cost governance through per-model and per-pod spend visibility, token-cost tracking, and anomaly alerting.
• Build automation and self-service paths to provide product teams with a defined, safe route to production.
• Transform recurring operational challenges into simple, reusable platform standards.
• Participate in architecture discussions, code reviews, and technical decision-making processes.

Required Qualifications and Experience

• A minimum of 4 years of experience in SRE, platform engineering, DevOps, or production infrastructure, with a proven track record of operating distributed systems in production environments.
• Hands-on experience with Kubernetes and cloud-native systems in a production setting.
• Familiarity with deploying machine learning projects.
• Strong command of CI/CD, GitOps, observability tools, and incident response procedures.
• Solid experience with infrastructure-as-code, secrets management, and networking concepts.
• Proficiency in writing automation or platform tooling in Python or a comparable language.
• Demonstrated production judgment, with the ability to make systems measurable, debuggable, repeatable, and safe to change.
• Ability to collaborate effectively across teams, clearly articulate trade-offs, and translate operational pain points into practical standards for engineers.

Additional Preferred Skills

• Experience with MLOps or ML platforms, including model serving, registries, evaluation, feature/data dependencies, drift monitoring, or ML pipelines.
• Familiarity with LLM applications or agentic systems, such as RAG, vector databases, tool calling, workflow orchestration, memory, traces, guardrails, or evaluation pipelines.
• Exposure to tooling such as OpenTelemetry, Prometheus, Grafana, MLflow, KServe, Ray, LiteLLM, vLLM, LangGraph, Arize Phoenix, or LangSmith.
• Experience with Kafka consumers, GPU workloads, inference optimization, model routing, or AI cost governance.
• Experience working within cross-functional product teams involving AI, backend, and frontend engineers.