Senior Software Engineer, Infrastructure (Data & AI)

Location: Seoul, South Korea

Company

Airwallex is an AI-native financial operating system providing infrastructure for global payments and financial products.

What you will do

• Design, build, and operate highly available data and AI infrastructure on Kubernetes and public cloud platforms.
• Develop scalable streaming, batch-processing, and real-time data platforms using Kafka, Spark, and Flink.
• Build AI gateways, model-routing layers, traffic management, rate limiting, authentication, observability, and usage controls.
• Create self-service platform capabilities that allow data, AI, and application teams to deploy and operate workloads independently.
• Collaborate across application, data, machine learning, security, and infrastructure teams to define durable platform capabilities.

Requirements

• 5+ years of experience in DevOps, SRE, or platform engineering with end-to-end ownership of production systems.
• Strong experience designing, operating, and troubleshooting production Kubernetes environments.
• Experience with distributed data infrastructure such as Kafka, Spark, or Flink, or with AI gateways and model-routing platforms.
• Hands-on experience with AWS, Google Cloud, or Microsoft Azure.
• Strong knowledge of cloud and container networking, distributed systems, infrastructure-as-code, automated delivery, and observability.
• Production programming experience in Go, Python, or Java, along with strong debugging, communication, and ownership skills.

Nice to have

• Experience building internal developer platforms and paved-road workflows.
• Experience with SGLang, vLLM, or NVIDIA Triton Inference Server.
• Knowledge of GPU scheduling, batching, model parallelism, memory management, autoscaling, and inference optimization.
• Experience improving the cost efficiency of large-scale data processing or AI inference workloads.
• Contributions to infrastructure, data-platform, Kubernetes, or AI-serving open-source projects.

Culture & Benefits

• Work on infrastructure supporting global payments, data platforms, and production AI applications.
• Collaborate across multiple engineering disciplines and international offices.
• Build reusable platform capabilities adopted by engineering teams.
• Focus on improving scalability, reliability, operational efficiency, observability, and cost visibility.