Senior Software Engineer, Infrastructure AI

About the role

Airwallex, the AI-native financial operating system used by more than 675,000 businesses, is hiring a Senior Software Engineer for its Infrastructure AI team. You will design and operate goal-oriented AI agents that automate SRE, DevOps and DBA workflows across the company's global infrastructure. The role is based in the Seattle office on Mondays, Wednesdays and Thursdays.

Key responsibilities

• Build goal-oriented infrastructure AI agents on Airwallex's internal agent platform to automate incident investigation, infrastructure provisioning, deployment orchestration, database operations and capacity management.
• Design reliable agent architectures with planning, reasoning, tool use, error recovery, safety guardrails, auditability and human-in-the-loop escalation.
• Integrate agents with Kubernetes, Terraform, cloud APIs (AWS, GCP, Aliyun), monitoring and observability platforms, databases and CI/CD pipelines through well-designed tool interfaces.
• Define and improve evaluation frameworks for agent effectiveness, including task completion, accuracy, time to resolution and escalation rates.
• Partner with SRE, DevOps and platform engineering teams to identify high-value workflows for automation.
• Help shape Airwallex's technical vision for AI-driven infrastructure operations.

Required profile

• 5+ years of professional software engineering experience.
• Strong system design skills and the ability to architect reliable, safe and scalable systems interacting with production infrastructure.
• Experience building agentic AI systems that plan, reason and execute multi-step tasks with large language models.
• Excellent communication and collaboration skills in a global, cross-functional environment.
• Comfortable owning the roadmap, making decisions with incomplete information and working across time zones.

Required skills

• Backend language such as Python, Go, Java or Kotlin.
• Cloud platforms (AWS, GCP, Aliyun), Kubernetes, Terraform and CI/CD.
• Preferred: agent orchestration frameworks (LangGraph, CrewAI, AutoGen), LLM APIs (OpenAI, Anthropic), observability tools (Grafana, Prometheus, Datadog, ELK), database administration and SRE practices.