Site Reliability Engineer - AI Agents

About the role

Join the AI Infrastructure team within Payward’s Data organization to design, build, and operate the production systems that power AI agents. You will work closely with AI, Agent Systems, and Data Engineering teams to ensure the platform is reliable, observable, and scalable for both internal tools and external‑facing products.

Key responsibilities

• Design, build, and operate the infrastructure layer supporting AI agent workflows in production.
• Ensure reliability, scalability, and observability of agentic systems across internal and external products.
• Develop platform services, APIs, SDKs, and self‑service capabilities for engineering teams.
• Manage compute, orchestration, and serving infrastructure for model inference and agent execution.
• Implement monitoring, alerting, and incident‑response procedures tailored to AI/ML workloads.
• Use Infrastructure as Code tools (e.g., Terraform) to provision and manage AWS resources.
• Build and maintain CI/CD pipelines for rapid, reliable deployment of AI services.
• Define guardrails, failure‑handling, and recovery patterns for LLM‑powered systems.
• Collaborate with AI and Data Engineering teams to harden experimental prototypes into production services.

Required profile

• Proven experience in site reliability or platform engineering for cloud‑native services.
• Strong understanding of production discipline for AI/ML workloads.
• Ability to work cross‑functionally with data, ML, and product teams.

Required skills

• AWS
• Terraform
• Infrastructure as Code
• CI/CD pipelines
• Monitoring and alerting
• Linux operating systems

What we offer

• Opportunity to shape the core AI infrastructure for a leading crypto platform.
• Collaborative environment with fast‑moving AI and data teams.
• Access to cutting‑edge technologies and large‑scale production systems.