Senior Site Reliability Engineer
Posted Updated
Description
Mozn is seeking an AI Senior SRE to own on-call and incident response while building agentic, LL-driven reliability improvements on our enterprise AI platform.
You will work hands-on in Kubernetes, cloud environments, and observability stacks, turning operational learnings into reusable agents with guardrails and human-in-the-loop controls.
Carry a normal on-call rotation and respond hands-on to incidents. Read and debug service code to identify real root causes and ship fixes in apps when needed. Design, build, and ship LLM-based agents that plug into Kubernetes and cloud stacks. Define the agent interfaces and safe wrappers around tools and APIs. Establish guardrails and human-in-the-loop thresholds for autonomous actions. Own agent evaluation, testing, and backtesting against historical incidents. Tune prompts, context, and tool schemas as agents evolve. Collaborate with SRE/Platform teams to identify candidate workflows. 3+ years building production software with LLMs - agentic workflows, tool calls, multi-step planning, RAG. Hands-on experience shipping real work with an agentic coding tool (Claude Code, Codex, or Kimi K2/K3). Strong Python for building agent tooling, wrappers, and orchestration. Real SRE experience: primary on-call responder, incident response, root cause analysis under pressure. Read and debug a service's codebase to locate root causes and ship fixes. Solid Kubernetes and cloud experience (AWS/GCP/OCI/Azure) and observability tooling expertise. Knowledge of guardrails for autonomous systems: permissions, gates, rollbacks, auditability. Ability to earn trust with technical stakeholders with incremental autonomy. Competitive compensation Top-tier health insurance Flexible work options Professional development budgetSkills
Sign in to read and join the discussion.