Site Reliability Engineer - AI Agents

📋 Description

• Design, build, and operate AI agent infrastructure in production.
• Ensure reliability, scalability, and observability of agent systems.
• Design and develop platform services, APIs, and SDKs for teams.
• Manage compute, orchestration, and serving for model inference.
• Implement monitoring, alerting, and incident response for AI workloads.
• Use Terraform to provision AWS infrastructure.

🎯 Requirements

• 5+ years in SRE/Infrastructure/Platform roles in production.
• Hands-on ML infrastructure, model serving, or MLOps in production.
• Experience building developer platforms, APIs, or SDKs.
• Strong platform engineering focus: dev experience, self-service infra, API-driven design.
• Terraform proficiency.
• Kubernetes and Docker experience in production.

🎁 Benefits

• Diverse, merit-based Payward culture.
• Equal opportunity employer.
• Remote-friendly, global Kraken team.
• Encourages applicants who don't meet all requirements.