AI Infrastructure Engineer
Core
Operate and scale the bank's Sovereign AI Platform, managing the Kubernetes control plane, distributed LLM inference, and user-facing AI surfaces (chatbots, notebooks) to ensure data sovereignty and regulatory compliance.
Role type
Senior IC AI Infrastructure Engineer (Platform Engineering)
Builds
Sovereign AI Platform (distributed inference, agentic workflows, notebooks, chatbots) and governed routing layers for external LLM providers.
Domain
Banking / Cloud-Native AI Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Kubernetes internals, distributed systems, cloud-native security, Infrastructure as Code, incident response, SLO definition, multi-cluster management, regulated environment operations
Preferred skills
LLM-d frameworks (vLLM, TGI, Triton, Ray Serve), JupyterHub/Open WebUI operation, Kubernetes-native agentic frameworks, external LLM provider integration, Python/Go/Rust/Java/C++
Technologies
Kubernetes, etcd, AAP, Terraform, Ansible, Apache Kafka, vLLM, TGI, NVIDIA Triton, Ray Serve, KServe, Agentgateway, Anthropic Claude API, OpenAI GPT API
Responsibilities
Design and operate distributed LLM inference on Kubernetes; harden user-facing AI surfaces (Open WebUI, JupyterHub); build and operate Agentgateway for external provider routing; implement content-safety and prompt-injection defenses; operate the Kubernetes control plane with HA sizing; define SLOs and lead incident response; automate platform provisioning via IaC.
Seniority
Senior, hands-on IC