Senior DevOps Engineer

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Deploy, manage, and enhance a microservices-oriented platform operating within Kubernetes clusters on AWS, GCP, and on-premises Rancher.

• Support and operate GPU-accelerated ML inference services utilizing Triton Inference Server and vLLM on RunPod, Scaleway, and Nebius.

• Create and uphold Docker images for all microservices while ensuring a reliable service lifecycle.

• Maintain and scale both development and production Kubernetes clusters.

• Engage in deployment troubleshooting, incident investigation, and performance optimization.

• Develop, sustain, and advance custom Helm charts for every service.

• Design and manage CI/CD pipelines utilizing GitHub and GitLab for on-premises client deployments.

• Ensure platform adherence to SOC 2 standards and enhance security and compliance procedures.

• Manage cluster access through NetBird VPN and implement role-based access control via group policies.

• Deploy and oversee infrastructure using Terraform and Ansible Infrastructure as Code (IaC) practices.

• Develop and consistently enhance observability systems incorporating Grafana, Prometheus, and the ELK stack.

• Continuously refine infrastructure across IaC, IAM, observability, and CI/CD.

• Work with technologies such as Python, Kubernetes, Linux, Docker, GitHub CI/CD, PostgreSQL, ClickHouse, Kafka, Superset, Terraform, and Ansible.

⛳️ Requirements

• A minimum of 5 years of experience in a DevOps and/or Site Reliability Engineering position.

• Strong hands-on experience in Linux system administration.

• Extensive experience in deploying, managing, and scaling Kubernetes in both cloud and bare-metal settings.

• Deep knowledge and practical experience with at least one leading cloud provider, preferably Google Cloud Platform.

• Experience with ML inference on GPU/CPU is a significant advantage.

• Proven track record of implementing SRE methodologies and constructing observability stacks using Grafana, Prometheus, and Loki.

• Strong commitment to GitOps, Infrastructure as Code (IaC), and CI/CD principles.

• Advanced proficiency in Terraform, Ansible, and Python.

• Capability to operate in high-uncertainty environments and quickly adapt to new technologies and patterns.

• Ability to analyze beyond DevOps functions and effectively debug and comprehend the product.

• Capacity to select technologies and architectural strategies based on long-term objectives.

• English proficiency is implied through private English lessons, though no explicit language requirement is stated.

🏝️ Benefits

• Award-winning AI products and a state-of-the-art technology stack.

• Fully remote work environment.

• 21 vacation days, in addition to public holidays and 5 sick days.

• Private English lessons through Preply.

• Fast-paced startup culture with enterprise-level stability.

• Rapid career advancement opportunities.

• Genuine ownership and direct impact from your work.