Senior DevOps Engineer

About the role

We are looking for a Senior DevOps Engineer to join our fast‑growing team that powers machine‑learning and speech‑technology products used by hundreds of millions worldwide. You will own the design, deployment, and operation of a multi‑cloud, hybrid Kubernetes platform that supports GPU‑based inference services.

Key responsibilities

• Deploy, operate, and evolve micro‑services platforms on Kubernetes clusters across AWS, GCP, and on‑prem Rancher environments.
• Run and support GPU‑based ML inference services (Triton Inference Server, vLLM) on RunPod, Scaleway, and Nebius.
• Build and maintain Docker images and custom Helm charts for all services.
• Design, implement, and maintain CI/CD pipelines using GitHub and GitLab.
• Ensure SOC 2 compliance, security hardening, and role‑based access control via NetBird VPN.
• Manage infrastructure as code with Terraform and Ansible.
• Develop observability stacks (Grafana, Prometheus, Loki, ELK) and lead incident investigation and performance troubleshooting.
• Continuously optimise IaC, IAM, observability, and CI/CD processes.

Required profile

• Minimum 5 years of experience in DevOps or Site Reliability Engineering.
• Strong hands‑on Linux system administration.
• Proven ability to work in high‑uncertainty, fast‑changing product environments.
• Proactive mindset with a focus on debugging beyond routine tasks.
• Strategic thinking to choose long‑term architectural solutions.

Required skills

• Linux
• Kubernetes (AWS, GCP, Rancher)
• GPU inference platforms (Triton Inference Server, vLLM)
• Cloud providers: AWS, Google Cloud Platform
• Docker & Helm
• GitHub, GitLab CI/CD
• Terraform, Ansible
• Python
• Grafana, Prometheus, Loki
• ELK stack (Elasticsearch, Logstash, Kibana)
• NetBird VPN
• PostgreSQL, ClickHouse, Kafka, Superset

What we offer

• Work with an experienced, award‑winning AI team.
• Access to cutting‑edge technologies in ML, speech, and cloud infrastructure.
• Opportunities to shape a new product from the ground up.