*VinSOC is looking for a DevSecOps / MLOps/ LLMOps Engineer to architect and scale cutting-edge cloud platforms at the intersection of AI and Cybersecurity.*
📍 Location: Technopark Tower, Gia Lam, Hanoi
**What You’ll Do**
- Define and execute the end-to-end DevSecOps / MLOps/
*LLMOps*
strategy (CI/CD, infrastructure, security, observability).
- Architect, deploy, and operate cloud infrastructure (AWS) with focus on scalability, high availability (HA), and security.
- Design and optimize CI/CD pipelines using Jenkins, GitLab CI, ArgoCD.
- Standardize and manage Kubernetes environments (EKS / on-prem), including GPU workloads, networking, ingress, and autoscaling.
- Implement Infrastructure as Code (Terraform, Ansible) for automated provisioning and operations.
- Build and maintain monitoring & observability systems (Prometheus, ELK/OpenSearch, Datadog).
- Drive DevSecOps best practices: SAST, DAST, container security, SBOM.
- Optimize infrastructure cost following FinOps principles.
- Collaborate closely with Engineering, AI, Data, and Security teams.
- Develop runbooks, disaster recovery (DR) plans, and design high availability architectures.
**What We’re Looking For**
- Bachelor’s degree in computer science, IT, or related fields
**Experience**
- 10+ years in DevOps / SRE / Platform Engineering.
- Proven experience operating
**large-scale production systems**
(AI/GPU workloads is a strong advantage).
**Technical Skills**
- Cloud & Infrastructure: Strong expertise in AWS / Azure / GCP; solid understanding of HA, DR, multi-region architecture.
- Containers & Orchestration: Hands-on experience with Docker & Kubernetes (EKS/AKS/on-prem); strong understanding of networking (CNI, ingress); service mesh is a plus.
- CI/CD: Experience with Jenkins, GitLab CI, ArgoCD; ability to design full pipelines
- Infrastructure as Code: Strong hands-on with
**Terraform**
(required); Ansible/Helm is a plus.
- Observability: Experience with Prometheus, Grafana, ELK/OpenSearch, Datadog; understanding of APM & distributed tracing (OpenTelemetry is a plus).
- Security: Solid knowledge of DevSecOps practices (SAST, DAST, container security)
- Experience building end-to-end
**MLOps/ LLMOps platforms**
- Familiarity with tools such as KServe, MLflow, Airflow, DVC.
- Understanding of model reproducibility, GPU workload automation, and advanced deployment patterns (canary, A/B testing, shadow traffic).
**Preferred**
**Internal Developer Platform (IDP)**
.
**AI/LLM in DevOps (AIOps, AI Agents)**
.
- Knowledge of Kafka, ClickHouse, or data pipelines.
- FinOps mindset and cost optimization experience.
- Relevant certifications (AWS / Azure / GCP, CKA / CKAD).
**Why Join VinSOC?**
- Work on cutting-edge platforms at the intersection of Cloud, AI, and Cybersecurity.
- Lead impactful initiatives with high ownership and real business impact.
- Opportunity to build and scale modern DevSecOps/MLOps platforms from the ground up.
- Dynamic, fast-growing environment with top-tier engineering talent.
