DevOps / SRE Engineer - AI Platform

> CP Axtra

• Nawamin Road, Thailand (Hybrid)
• Full-time

Workplace: hybrid

Department: Technology

Description

The DevOps / SRE Engineer owns the operational substrate of an AI-native retail decisioning platform - infrastructure, CI / CD, observability, cost meter, and incident response for a system that runs production agents taking real business actions. The role builds on the enterprise Terraform standard, CI / CD spine, and FinOps tagging policy rather than reinventing parallel infrastructure.

Remote candidates outside of Thailand are welcome to apply.

Key Responsibilities:

• Adopt the enterprise Terraform standard and module library for all platform infrastructure; author platform-specific modules where needed (agent runtime, vector DB, knowledge graph); run drift detection weekly.

• Build platform-specific CI / CD pipelines on the enterprise spine - service deploys, agent deploys, eval-gate enforcement; integrate eval gates so no agent reaches production without eval pass.

• Operate rollback orchestration with sub-15-minute recovery; quarterly game days.

• Own the platform observability stack - OpenTelemetry, Langfuse for LLM traces, custom dashboards for per-agent cost.

• Implement the per-agent cost meter end-to-end - token counts, vector queries, model inference, downstream LLM Gateway costs; surface cost data to the enterprise GenAI cost dashboard.

• Stand up the platform on-call rotation; author runbooks for every production agent and service; lead incident response with measurable corrective actions.

• Implement platform cost-tagging policy consistent with the enterprise standard (team, domain, environment, project, agent, suite, persona); report monthly to Cost Review.

• Drive cost optimisation - right-sizing, caching, model routing decisions, reserved compute.

Requirements

• Bachelor's or Master's degree in Computer Science, Engineering, or a related discipline.

• 5+ years SRE / DevOps with production ownership.

• Terraform at scale - modules, state, drift, environment promotion.

• CI / CD for data + ML / AI services (GitLab CI / CD or comparable).

• Cloud platform (Azure preferred; AWS / GCP transferable).

• Observability - OpenTelemetry, Langfuse (or comparable LLM traces), custom dashboards.

• FinOps - tagging policies, attribution, optimisation.

• Incident response - on-call, post-mortems, runbook authorship.

Preferred

Qualifications

• AI / agent platform SRE experience; cost-meter / chargeback systems built or operated.

• Multi-cloud production experience; open-source contributions to IaC / observability tooling.

• AI / ML / agent system observability instrumentation (LLM cost, agent cost, eval scores).

• Vendor certifications such as HashiCorp Terraform Associate / Professional, Azure Solutions Architect Associate, or Databricks Data Engineer Professional.

Apply

[Apply at CP Axtra](https://apply.workable.com/joinmakropro/j/A1B401274A/apply)