DevOps / Infrastructure Engineer

About BTSE: BTSE Group is a global leader in fintech and blockchain technology, anchored by three core business pillars: Exchange, Payments, and Infrastructure Development. Serving over 100 corporate clients worldwide, we provide white-label exchange and payment solutions. Our offerings encompass everything from exchange infrastructure hosting and development to custody, wallets, payments, blockchain integration, trading, and more. We are looking for talented professionals in marketing, operations, customer support, and other departments. The roles offered may be on-site, remote, or hybrid, in collaboration with our local partner. About the opportunity: You keep the platform running reliably. For the first client operating in crypto markets, this means 24/7 uptime with zero maintenance windows. You build multi-tenant Kubernetes infrastructure with per-tenant namespace isolation, manage GPU scheduling for AI model serving, set up CI/CD for rapid iteration, and own monitoring and on-call. You also automate tenant provisioning so that scaling from one client to ten is an operational exercise, not an engineering project. About BTSE: BTSE Group is a global leader in fintech and blockchain technology, anchored by three core business pillars: Exchange, Payments, and Infrastructure Development. Serving over 100 corporate clients worldwide, we provide white-label exchange and payment solutions. Our offerings encompass everything from exchange infrastructure hosting and development to custody, wallets, payments, blockchain integration, trading, and more. We are looking for talented professionals in marketing, operations, customer support, and other departments. The roles offered may be on-site, remote, or hybrid, in collaboration with our local partner.   About the opportunity: You own the AI core: model serving, the retrieval-augmented generation (RAG) pipeline, prompt engineering, and the feedback-to-training pipeline. In Phase 1, you make the base model perform as well as possible through context engineering — system prompts, few-shot exemplars, and retrieval optimisation — without modifying model weights. You also design the custom model training workflow so that enterprise clients can train their own fine-tuned models in Phase 2. This is the highest-leverage individual contributor role on the founding team. Responsibilities

Set up a multi-tenant Kubernetes cluster: shared services namespace, per-tenant namespaces for isolated workloads, GPU node pools for model inference.

Build CI/CD pipeline: source control → container build → automated deployment with zero-downtime rolling updates.

Configure GPU management: scheduling, resource quotas per tenant, device plugins.

Set up comprehensive monitoring: per-tenant metrics, SLA tracking, data pipeline health, GPU utilisation, API latency percentiles, WebSocket connection stability.

Implement backup and disaster recovery: cross-region replication, automated database backups.

Build tenant provisioning automation: scripted creation of new tenant namespaces, storage, network policies, and service accounts.

Security hardening: network policies between namespaces, vulnerability scanning, audit logging.

24/7 on-call during initial pilot (rotating with Tech Lead).

Requirements

4+ years DevOps/SRE; Kubernetes cluster operations including multi-tenant patterns.

GPU workloads on Kubernetes (GPU Operator, device plugins, resource scheduling).

CI/CD pipelines: GitHub Actions, ArgoCD or FluxCD.

Terraform IaC.

On-call experience and incident management.

Nice to have

Kubernetes namespace isolation and network policies for multi-tenancy.

24/7 systems experience (crypto, gaming, or global SaaS).

Monitoring WebSocket-heavy architectures and streaming data pipelines.

GPU cluster management for ML inference.

#LI-MC1 Apply To This Job