Site Reliability Engineer – AI Platform

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

📋 Description

• Oversee and assist with production platform systems

• Establish and monitor SLIs, SLOs, and error budgets related to availability, latency, and throughput

• Create and sustain dashboards, alerts, and telemetry to analyze AI solution performance and model utilization

• Track token usage, request latency, throttling, quota limits, error rates, cost attribution, and signals for output quality or drift

• Operate and maintain Kubernetes clusters along with Azure cloud services

• Oversee capacity planning, autoscaling, upgrades, workload health, and resource optimization

• Collaborate with DevOps engineers to automate and enhance GitHub Actions CI/CD pipelines

• Integrate reliability checks, automated testing, progressive delivery, and rollback strategies

• Utilize Terraform and other infrastructure-as-code tools for provisioning and managing cloud environments

• Engage in on-call duties and incident response activities

• Facilitate blameless post-incident reviews, maintain runbooks, and implement corrective measures

• Conduct capacity planning, load and failure testing, and assess disaster recovery preparedness

• Work in tandem with developers, data scientists, security, and enterprise architecture teams

• Create operational documentation for platform users

⛳️ Requirements

• Bachelor's degree in Computer Science, Engineering, Information Systems, or a related discipline

• Over 5 years of hands-on experience in site reliability engineering, DevOps, or cloud operations

• Extensive practical experience managing production workloads on Kubernetes, including deployment, configuration management, networking, autoscaling, cluster upgrades, and troubleshooting

• Proven experience operating production workloads in a leading public cloud environment: Azure, AWS, or GCP

• Proficiency in observability tools such as Azure Monitor, Prometheus, Grafana, or Dynatrace

• Familiarity with OpenTelemetry-based tracing, metrics collection, and logging

• Experience in defining SLIs, SLOs, and error budgets

• Skill in developing actionable alerts that minimize noise

• Experience with CI/CD pipelines, preferably using GitHub Actions

• Knowledge of infrastructure as code, especially Terraform

• Scripting or programming background in Python, Bash, PowerShell, or Go

• Strong incident management and troubleshooting abilities

• Experience with on-call rotations and conducting blameless post-incident reviews

• Curiosity and eagerness to understand the behavior of AI solutions and models in production

• Preferred: Familiarity with Azure services, monitoring AI/ML or generative AI workloads, Helm, KEDA, service meshes, GPU-enabled workloads, DevSecOps, secrets management, policy as code, supply chain security, and relevant certifications

🏝️ Benefits

• Flexible and supportive work environment

• Emphasis on well-being

• Be Well programs that promote financial, mental, physical, and social health

• Customized development objectives and ongoing feedback

• Certification opportunities with Microsoft, Google, and Amazon

• Coaching and practical learning experiences

• Access to cutting-edge learning opportunities

• Tools for career progression and professional development assistance

• Full-time employment