Oivan is looking for a Senior DevOps Engineer to own the platform that runs our internal technology, including the AI agents we build and operate for ourselves. You will report directly to the CTO and shape how Oivan ships, runs and secures its own systems. This is an internal technology role, not a client delivery position. You will build and run the platform behind Oivan's own products and internal systems, the pipelines, clusters, cloud infrastructure and observability that everything else depends on.
🏢 About Oivan
🎯 The Role
You will be the engineer who takes AI agents from a working prototype to something that runs reliably in production, with the model endpoints, orchestration, data stores, guardrails and monitoring that requires. You report directly to the CTO, which means you have a real say in platform direction, technology choices and build-versus-buy decisions.
✅ Key Responsibilities
Design, build and operate the CI/CD pipelines and deployment platform for Oivan's internal applications and services.
Deploy, run and monitor AI agents and LLM-backed services in production, model endpoints, orchestration layers, vector stores, evaluation and the guardrails around them.
Own our Kubernetes clusters end to end: provisioning, upgrades, autoscaling, networking, ingress, secrets and workload management.
Manage cloud infrastructure, with clear cost visibility and sensible guardrails.
Build observability that people actually use, metrics, logs, traces, alerting and dashboards.
Automate everything repeatable with Infrastructure as Code.
Harden the platform: identity and access, secrets management, network policy, patching and vulnerability management.
Support the internal front-ends and the services behind them through build, release and runtime.
Work with the CTO on platform roadmap, tooling decisions and where we build versus buy.
Act as the escalation point for internal platform incidents, and drive the follow-up that stops them recurring.
📌 Required Qualifications
5+ years in DevOps, platform engineering or SRE, operating at strong medior to senior level.
Hands-on Kubernetes in production, GKE, EKS or on-premise. Not just deploying to a managed cluster, but owning it
CI/CD ownership — designing and running pipelines, not only using them.
Infrastructure as Code — Terraform, Pulumi or equivalent.
Cloud platform experience at production scale.
Linux administration and scripting — Bash and Python.
Containers and registries — Docker, image hygiene, supply chain basics.
Observability — Prometheus, Grafana, centralized logging and alerting.
Secrets management and identity across services and environments.
Advanced English and strong communication. You will work directly with the CTO and across teams, and you will be expected to explain technical decisions clearly to non-specialists.
Based in Thailand, able to work from Khon Kaen. Bangkok is also a possibility for the right candidate.
⭐ Desirable Experience
Deploying and operating AI agents or LLM-backed services in production — this is the fastest way to make an impact here.
Please let Oivan Group know that you found this role at devopsprojectshq.com as a way to support us, so we can keep providing you with awesome DevOps jobs.
Never miss a job
Join 2,000+ DevOps developers getting weekly alerts for remote and US/EU roles, Kubernetes, AWS, Terraform, filtered for your stack.
🔒 Need an IP to whitelist?
Get a dedicated static EU outbound IP for Banks, payments, EHRs, APIs, AI.
