Senior GPU Systems & Fabric Engineer

About the role

Bitdeer is seeking a Senior GPU Systems & Fabric Engineer to bridge its physical GPU and network infrastructure with the Kubernetes abstraction layer. You will create the high‑performance hardware foundation that enables AI‑native cloud computing at scale.

Key responsibilities

• Architect and maintain NVIDIA/AMD GPU device plugins and Kubernetes Operators for exposing hardware capabilities.
• Configure and optimize high‑performance host networking stacks (RDMA, SR‑IOV, RoCEv2, InfiniBand) to achieve line‑rate throughput for distributed AI training.
• Build automated hardware remediation pipelines using DCGM telemetry to detect and reset degraded GPU/NIC components.
• Implement GPU slicing technologies (MIG, vGPU) for multi‑tenant inference workloads.
• Profile and tune kernel parameters, device drivers, and runtime libraries (CUDA, NCCL) to eliminate bottlenecks.
• Collaborate with scheduling and storage teams for topology‑aware placement and efficient data movement.
• Define standards for bare‑metal provisioning, BIOS/firmware updates, and OS hardening.
• Lead investigations into performance issues across hardware, fabric, and software, and mentor team members.

Required profile

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering or related field.
• 5+ years of systems engineering experience with strong Linux kernel knowledge.
• Hands‑on experience with NVIDIA H100/A100 GPUs, CUDA runtimes, and high‑speed networking (RDMA, InfiniBand).
• Proven ability to operate, debug, and scale bare‑metal systems in large‑scale production or HPC environments.
• Experience with infrastructure automation tools such as Terraform and Ansible.

Required skills

• Linux kernel internals
• C and Go programming
• GPU architectures (NVIDIA, AMD)
• CUDA, NCCL
• RDMA, SR‑IOV, RoCEv2, InfiniBand
• Kubernetes device plugin architecture
• DCGM telemetry
• GPU slicing (MIG, vGPU)
• Terraform, Ansible, CI/CD pipelines