Site Reliability Engineer - AI Agents

You will be responsible for building and operating the infrastructure backbone that supports AI agent systems in production, ensuring reliability, scalability, and usability across engineering teams.

• Design, build, and operate cloud-native infrastructure supporting AI agent workflows, including orchestration, execution, and model serving
• Ensure high reliability, scalability, and observability of distributed agentic systems across internal and external products
• Develop platform capabilities such as APIs, SDKs, and self-service tools to enable efficient consumption of AI infrastructure
• Manage compute, deployment, and serving infrastructure for AI and ML workloads in production environments
• Build and maintain CI/CD pipelines enabling safe, reliable, and rapid deployment of AI services and agent workflows
• Implement Infrastructure as Code using tools such as Terraform to provision and manage AWS-based environments
• Design and operate observability systems, including monitoring, alerting, and incident response tailored to AI/ML workloads
• Define reliability patterns, failure handling mechanisms, and recovery strategies for LLM and agent-based systems
• Collaborate with AI, Data Engineering, and Product teams to transition experimental prototypes into production-grade systems
• Manage Kubernetes-based container orchestration environments to ensure efficient scaling and deployment of services
• Implement security controls and access management best practices across infrastructure layers
• Document system architecture, operational procedures, and best practices to support platform adoption and knowledge sharing

Requirements

The ideal candidate is a strong infrastructure or SRE engineer with platform engineering experience and exposure to ML or AI-driven systems in production.

• 5+ years of experience in Site Reliability Engineering, Platform Engineering, Infrastructure Engineering, or similar roles
• Hands-on experience supporting ML infrastructure, model serving, or MLOps pipelines in production environments
• Experience building developer platforms, internal tooling, APIs, or SDKs used at scale by engineering teams
• Strong understanding of platform engineering principles, including self-service infrastructure and developer experience design
• Proficiency with Infrastructure as Code tools, particularly Terraform
• Strong experience with Kubernetes and containerized environments (Docker)
• Solid cloud infrastructure experience, preferably AWS
• Strong scripting skills (bash/shell) and proficiency in at least one programming language (Python preferred)
• Experience designing and operating observability, monitoring, and alerting systems
• Experience with incident response, on-call rotations, and production reliability ownership
• Strong collaboration skills across data, AI, and engineering organizations
• High ownership mindset and ability to operate in fast-paced, high-stakes production environments
• Familiarity with AI agent systems, LLM-based applications, or orchestration frameworks is a strong plus

Benefits

• Competitive compensation package with performance-based incentives
• Fully remote working model across eligible countries, including Brazil
• Comprehensive healthcare coverage (medical, dental, and vision where applicable)
• Retirement savings programs with employer contributions (where applicable)
• Flexible PTO policy and paid company holidays
• Mental health and wellness support programs
• Learning and development budget for professional and technical growth
• Opportunity to work on cutting-edge AI agent infrastructure at global scale
• Distributed, high-ownership engineering culture with strong collaboration across teams
• Exposure to advanced platform engineering and applied AI systems;