AI Infrastructure Engineer (Kubernetes)

TL;DR

AI Infrastructure Engineer (Kubernetes): Designing and operating the bank's sovereign AI platform and Kubernetes-native middleware fabric with an accent on distributed LLM inference, GPU utilization, and secure agentic workflows. Focus on building governed access to AI capabilities, ensuring compliance with AI Act and DORA regulations, and maintaining high-availability control planes.

Location: Must be based in Gland, Switzerland

Company

hirify.global is the Swiss leader in online banking, providing trading, investing, and banking services to over 650,000 clients through performant and secured digital platforms.

What you will do

• Design, deploy, and operate distributed LLM inference on Kubernetes, optimizing for throughput and GPU utilization.
• Operate and harden the user-facing AI surface, including Open WebUI chatbots and JupyterHub notebooks.
• Build and operate a governed routing layer for external LLM providers, enforcing traffic policies and cost controls.
• Implement content-safety, prompt-injection defenses, and audit controls for AI compliance.
• Manage the Kubernetes control plane with high-availability sizing and multi-cluster management.
• Define SLOs, lead incident response, and automate platform provisioning using Infrastructure as Code.

Requirements

• 7+ years of experience in infrastructure or platform engineering, with at least 3 years operating production Kubernetes or ML-serving workloads at scale.
• Proven experience in regulated industries such as banking, telco, or government.
• Strong understanding of Kubernetes internals, container runtimes, distributed systems, and cloud-native security.
• Excellent interpersonal skills for influencing decision-making across technical and business teams.
• Must be able to work onsite in Gland, Switzerland.

Nice to have

• Hands-on experience with distributed inference frameworks like vLLM, TGI, NVIDIA Triton, or Ray Serve.
• Proficiency in Python, Go, Rust, Java, or C++.
• Experience with Infrastructure as Code tools like Ansible or Terraform.
• Familiarity with event streaming (Apache Kafka) and observability stacks.

Culture & Benefits

• Work in a flexible, multicultural environment without a strict dress code.
• Opportunity to have a significant impact on the banking industry and AI governance.
• Participation in a 24x7 on-call rotation.
• Equal opportunity employer welcoming diverse backgrounds and perspectives.