Site Reliability Engineer - AI Platform

Location: Fully remote, based in Sao Paulo, Brazil

Company

hirify.global operates and modernizes mission-critical technology systems for large businesses, using AI-powered insight to support smarter decisions and faster innovation.

What you will do

• Monitor enterprise AI platform health and define and track SLIs, SLOs, and error budgets for availability, latency, and throughput.
• Design and maintain dashboards, alerts, and telemetry for AI solution behavior and model usage, including token consumption, latency, throttling, quotas, errors, cost attribution, output quality, and drift signals.
• Operate Kubernetes clusters and public cloud services, including capacity planning, autoscaling, upgrades, workload health, API management, managed model services, and resource optimization.
• Partner with DevOps engineers to improve GitHub Actions CI/CD pipelines with reliability checks, automated testing, progressive delivery, and rollback practices.
• Provision and manage secure, compliant cloud environments with Terraform and other infrastructure-as-code tools.
• Participate in on-call and incident response, lead blameless post-incident reviews, maintain runbooks, and drive capacity, resilience, load testing, disaster recovery, and corrective-action work.

Requirements

• Bachelor's degree in Computer Science, Engineering, Information Systems, or a related field.
• 5+ years of practical experience in site reliability engineering, DevOps, or cloud operations.
• Strong hands-on experience running production workloads on Kubernetes, including deployment and configuration management, networking, autoscaling, cluster upgrades, and troubleshooting.
• Experience operating production workloads in a major public cloud such as Azure, AWS, or GCP.
• Proficiency with observability tools such as Azure Monitor, Prometheus, Grafana, or Dynatrace, including OpenTelemetry-based tracing, metrics, and logging.
• Experience defining SLIs, SLOs, and error budgets and building actionable, low-noise alerting.
• Experience with CI/CD pipelines, infrastructure as code, scripting or programming with Python, Bash, PowerShell, or Go, and pipeline reliability collaboration with DevOps engineers.
• Strong incident management, troubleshooting, and communication skills, including on-call rotations and blameless post-incident reviews.
• Curiosity and willingness to learn how AI solutions and models behave in production; prior AI or machine learning experience is not required.

Nice to have

• Experience with Azure Kubernetes Service, Azure API Management, or Azure AI Foundry.
• Experience monitoring AI/ML or generative AI workloads, including model quality, drift, safety, and cost metrics.
• Experience with Helm, KEDA, service meshes, and GPU-enabled Kubernetes workloads.
• Experience with DevSecOps practices, including secrets management, policy as code, and supply chain security.
• Certifications such as Certified Kubernetes Administrator, Azure Administrator, or Azure DevOps Engineer Expert.

Culture & Benefits

• Fully remote work with a flexible, supportive, and hybrid-friendly culture.
• Be Well programs supporting financial, mental, physical, and social health.
• Career development through personalized goals, continuous feedback, coaching, and hands-on experience.
• Access to learning opportunities and certifications from Microsoft, Google, and Amazon.
• Inclusive culture focused on belonging, empathy, continuous learning, and shared success.