Software Engineer, Infrastructure AI

Responsibilities

• Build autonomous infrastructure AI agents on the Quartermaster platform for SRE, DevOps, and DBA workflows.
• Design safe and reliable agent architectures with planning, reasoning, tool use, error recovery, auditing, and human-in-the-loop escalation.
• Integrate agents with Kubernetes, Terraform, cloud APIs, databases, monitoring systems, and deployment pipelines.
• Create metrics and evaluation frameworks for agent effectiveness, accuracy, resolution time, and escalation rates.
• Partner with SRE, DevOps, and platform engineering teams to identify and automate high-value operational workflows.
• Contribute to Airwallex’s technical vision for agentic AI in infrastructure operations.

Requirements

• At least 3 years of professional software engineering experience.
• Strong backend proficiency in Python, Go, Java, or Kotlin.
• Practical experience with AWS, GCP, or Aliyun; Kubernetes; Terraform; and CI/CD systems.
• Strong system design skills for reliable, safe, and scalable agent systems operating against production infrastructure.
• Experience building agentic AI systems that plan, reason, use tools, and execute multi-step tasks with LLMs.
• Experience with agent orchestration frameworks such as LangGraph, CrewAI, AutoGen, or custom frameworks, and LLM APIs such as OpenAI or Anthropic.
• Experience with observability and monitoring systems such as Grafana, Prometheus, Datadog, or the ELK stack.
• Database administration or automation experience, including schema migrations, query optimization, or backup and recovery.
• Understanding of SRE practices such as incident response, runbooks, postmortems, SLOs, and SLIs.
• Strong communication and cross-functional collaboration skills in a global environment.

Benefits

• Hybrid work arrangement based in Seattle, Washington.
• Opportunity to join the infrastructure AI initiative at its early stage and shape autonomous infrastructure systems.