Senior AI Platform Reliability Engineer (Kubernetes + GPU)

BITDEER AI PTE. LTD.; Singapore; On-site; SGD 180,000 - 260,000; Full time

Benefits offered by this job

Training & mentoring

Competitive benefits

Growth opportunities

Job summary

Bitdeer Technologies Group in Singapore seeks a Senior AI Platform Engineer to keep the MaaS inference platform reliable under real customer traffic. This role owns production stability across gateway, inference-proxy, control plane, model deployments, GPU clusters, and multi-region operations.

Responsibilities include operating Kubernetes-based MaaS environments, defining SLOs, and driving safe rollouts with canaries and fast rollback.

Qualifications

• 6+ years in SRE, platform engineering, or infrastructure engineering for production cloud services.
• Deep Kubernetes experience, including Helm, Argo CD/GitOps, CNI/ingress, secrets, storage, and workload scheduling.
• Hands-on experience operating GPU, AI infrastructure, or HPC workloads is strongly preferred.
• Strong observability skills with Prometheus/VictoriaMetrics, OpenTelemetry, logs, traces, and incident diagnosis.
• Comfortable with Go, Python, Bash, Linux networking, and production automation.
• Proven ability to design reliable systems with clear SLOs, operational ownership, and post-incident follow-through.

Responsibilities

• Operate and harden Kubernetes-based MaaS production environments across CPU platform nodes, edge ingress, and regional GPU tiers.
• Define and own SLOs, alerting, dashboards, run books, and incident response for API availability, latency, error rate, capacity, and GPU health.
• Improve rollout safety for model/runtime/platform changes using canaries, fallback, health-aware routing, maintenance mode, and fast rollback.
• Drive capacity planning for GPU utilization, burst traffic, quota/rate limits, cross-region latency, and customer growth.
• Automate repetitive operations through Helm, Argo CD, operators, scripts, and self-healing workflows.
• Partner with runtime and performance engineers to debug incidents from public API edge to model worker.

Skills

Kubernetes

Helm

Argo CD

GitOps

CNI/Ingress

Observability

Prometheus

OpenTelemetry

Go

Python

Bash

Linux networking

Automation

SRE

GPU/AI infrastructure

Tools

Argo CD

Prometheus

VictoriaMetrics

OpenTelemetry

Git

Job description

Bitdeer Technologies Group in Singapore seeks a Senior AI Platform Engineer to keep the MaaS inference platform reliable under real customer traffic. This role owns production stability across gateway, inference-proxy, control plane, model deployments, GPU clusters, and multi-region operations.

Responsibilities include operating Kubernetes-based MaaS environments, defining SLOs, and driving safe rollouts with canaries and fast rollback.