Trivita AI is hiring Middle/Senior DevOps Engineers with experience in production Kubernetes, Cloud, Terraform, GitOps, CI/CD, and AI infrastructure.
Trivita AI develops AI-powered products and platforms for businesses, including AI assistants, workflow automation agents, knowledge search, and speech recognition. Our systems combine Python backends with commercial and self-hosted LLMs running on GPUs, deployed across Kubernetes, cloud platforms, and on-premise infrastructure.
As a Middle/Senior DevOps Engineer, you will design, deploy, and operate Kubernetes platforms supporting Trivita AI's products across AWS, GCP, Azure, and private cloud environments. The role focuses on CPU/GPU infrastructure, Infrastructure as Code, GitOps, platform security, observability, and SLO-driven operations.
Job description
Infrastructure and Kubernetes management
- Design, provision, and operate Kubernetes clusters across AWS, GCP, Azure, private cloud, and bare-metal environments.
- Manage node lifecycles, Kubernetes upgrades, and high-availability operations.
- Build and manage reproducible infrastructure using Terraform/OpenTofu and Ansible.
- Implement GitOps workflows using ArgoCD, Helm, and Kustomize across DEV, UAT, and PROD environments, including Canary/Blue-green deployments and rollback.
- Develop and optimize CI/CD pipelines, container image builds, and private registries.
Monitoring, security, and optimization
- Implement monitoring, logging, tracing, and alerting using Prometheus, Grafana, OpenTelemetry, and related tools.
- Define SLIs, SLOs, error budgets, and actionable alerts for production services.
- Manage PostgreSQL, Redis, Elasticsearch/OpenSearch, storage systems, backups, and recovery testing.
- Configure Kubernetes networking, including CNI, ingress, Gateway API, TLS, DNS, and network policies.
- Implement security controls such as RBAC, IAM, Pod Security Standards, image scanning, image signing, and secrets management.
- Support technical evidence collection for ISO/IEC 27001 and SOC 2 audits.
- Optimize CPU/GPU resource allocation, autoscaling, and infrastructure costs.
- Operate GPU workloads using NVIDIA GPU Operator, supporting vLLM and speech recognition services.
Operations and continuous improvement
- Participate in on-call rotations, respond to production incidents, and maintain runbooks and postmortems.
- Automate repetitive operational tasks using Bash or Python.
- Apply AI coding assistants to scripting, infrastructure configuration, code reviews, and debugging while validating outputs before production deployment.
- Collaborate with engineering teams to improve reliability, scalability, security, and operational efficiency.
Requirements
Experience and technical skills
- Middle: 3+ years of DevOps/SRE experience.
- Senior: 5+ years of DevOps/SRE experience.
- At least 2 years of hands-on Kubernetes operations in production, including version upgrades and incident response.
- Deep understanding of Kubernetes internals, containers, networking, and Linux troubleshooting.
- Hands-on experience with AWS, GCP, or Azure, including VPC, IAM, and managed Kubernetes.
- Production experience with Terraform/OpenTofu, Helm, and ArgoCD or equivalent GitOps tools.
- Proficiency in Prometheus, Grafana, centralized logging, and SLI/SLO-based monitoring.
- Ability to develop automation scripts using Bash or Python.
- Proficiency in AI coding assistants for scripting, reviewing, and debugging, with proper output validation and compliance with data security policies.
- Ability to read technical documentation in English.
Level-specific expectations
Middle DevOps Engineer
- Operate and improve existing Kubernetes clusters, CI/CD pipelines, and monitoring systems.
- Handle incidents using established runbooks and operational procedures.
- Deliver infrastructure changes through reviewed IaC/GitOps workflows.
Senior DevOps Engineer
- Design multi-cloud platform architectures for scalability and reliability.
- Define SLOs, disaster recovery strategies, security controls, and cost optimization plans.
- Lead major incident response and establish standardized deployment workflows.
- Mentor engineers and provide technical leadership.
Technology stack
- Container & Orchestration: Kubernetes, EKS, GKE, AKS, RKE2, Docker.
- Infrastructure as Code: Terraform, OpenTofu, Ansible.
- GitOps & CI/CD: ArgoCD, Argo Rollouts, Helm, Kustomize, GitHub Actions, GitLab CI.
- Monitoring & Observability: Prometheus, Grafana, OpenTelemetry, VictoriaLogs, Fluent Bit.
- Security & Networking: Cilium, Traefik, cert-manager, Kyverno, Trivy, cosign, Vault.
- Database & Storage: PostgreSQL, Redis, Elasticsearch/OpenSearch, Longhorn.
- AI Infrastructure: NVIDIA GPU Operator, vLLM, KEDA, Karpenter.
First 6 months expectations
- Manage all assigned infrastructure through IaC/GitOps, eliminating manual changes.
- Establish SLOs, actionable alerts, and CPU/GPU cost dashboards for core services.
- Complete at least one documented disaster recovery drill and one zero-downtime Kubernetes upgrade.
Preferred qualifications
- Experience operating GPUs on Kubernetes and deploying vLLM, Ray, or KServe.
- Experience with OpenStack, private cloud, or bare-metal infrastructure.
- Knowledge of Cilium/eBPF, service mesh, or Gateway API.
- Experience with runtime security, SLSA, or Kubernetes cluster backups using Velero.
- Familiarity with Crossplane or Cluster API.
- CKA/CKS or AWS, GCP, or Azure certifications.
- Experience supporting ISO/IEC 27001 or SOC 2 audits for infrastructure handling sensitive data.
Contact information
- Address: No. 01, Street 104, Quarter 3, Binh Trung Ward, Ho Chi Minh City
- Phone: [protected info]