SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Airwallex is a unified payments and financial platform serving over 250,000 global businesses. The Infrastructure & Productivity team is pioneering an AI agent ecosystem to automate infrastructure operations across the engineering organization.
In this role, you will design, build, and operate goal-oriented AI agents that automate SRE, DevOps, and DBA workflows across Airwallex's global infrastructure. You won't perform operations work yourself—you'll build the AI systems that do it autonomously. Your agents will investigate incidents, provision infrastructure, manage databases, execute deployments, and handle operational tasks that traditionally require human intervention.
You'll work on Quartermaster, Airwallex's internal agent platform, building domain-specific agents that interact with real infrastructure tooling including Kubernetes, Terraform, cloud APIs, databases, and monitoring systems. This requires deep thinking about agent architecture: planning and reasoning loops, tool selection and execution, safety guardrails, human-in-the-loop escalation, and reliability in production infrastructure environments.
Key responsibilities include:
- Design and implement autonomous agents for SRE, DevOps, and DBA workflows (incident investigation, infrastructure provisioning, deployment orchestration, database operations, capacity management)
- Build robust agent loops with planning, reasoning, tool-use, error recovery, and human escalation for safety and reliability
- Integrate agents with infrastructure tooling (Kubernetes, Terraform, AWS/GCP/Aliyun APIs, monitoring platforms, databases, CI/CD pipelines)
- Define and measure agent effectiveness metrics (task completion rate, accuracy, time-to-resolution, escalation rate)
- Partner with SRE, DevOps, and platform engineering teams to identify high-value automation workflows
- Contribute to the technical vision for infrastructure AI at Airwallex
Requirements:
- 3+ years of professional software engineering experience with strong proficiency in backend languages (Python, Go, Java, or Kotlin)
- Practical experience with cloud platforms (AWS, GCP, or Aliyun), container orchestration (Kubernetes), infrastructure-as-code (Terraform), and CI/CD systems
- Strong system design skills for architecting reliable, safe, and scalable agent systems interacting with production infrastructure
- Excellent communication and collaboration skills in cross-functional, global teams
Preferred qualifications:
- Hands-on experience building agentic AI systems with autonomous planning, reasoning, and multi-step task execution using LLMs
- Experience with agent orchestration frameworks (LangGraph, CrewAI, AutoGen, or custom frameworks) and LLM APIs (OpenAI, Anthropic)
- Experience with observability and monitoring systems (Grafana, Prometheus, Datadog, ELK stack)
- Database administration or automation experience (schema migrations, query optimization, backup/recovery)
- Understanding of SRE practices (incident response, runbooks, postmortems, SLOs/SLIs)
- Forward-thinking perspective on agent reliability, safety, evaluation, and autonomous infrastructure systems
