Remote GPU Kubernetes Infrastructure Engineer

Zekai; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Weekly lunch stipend

Health and dental benefits

RRSP matching

Parental leave (100%)

Enrichment stipend

6 weeks paid vacation

Home office stipend

Remote-friendly offices

Job summary

Cohere is seeking a remote-friendly infrastructure engineer to deploy and operate GPU Kubernetes clusters across clouds, ensuring reliability and cost-efficiency. You will work with AI researchers and ML engineers to improve stability of Cohere's foundation models.

The role emphasizes automation, on-call readiness, and collaboration across hardware partners. Strong Python/Go experience is valued, as is previous work with ML teams.

Qualifications

• Run GPU Kubernetes clusters for ML/HPC workloads.
• Debug Linux, networking, and performance issues; RDMA/NCCL knowledge a plus.
• Write software in Python or Go; contribute to open-source projects.

Responsibilities

• Deploy and operate GPU Kubernetes clusters across clouds.
• Collaborate with cloud providers and hardware partners on reliability and cost.
• Automate node, GPU, and fabric fault detection and remediation.
• Improve fleet utilization and time to repair faulty nodes.
• Troubleshoot production failures and performance issues to improve operability.

Skills

GPU Kubernetes

Linux debugging

Networking troubleshooting

Python or Go

Researcher/ML collaboration

Tools

Kubernetes

RDMA

NCCL

Job description

Cohere is seeking a remote-friendly infrastructure engineer to deploy and operate GPU Kubernetes clusters across clouds, ensuring reliability and cost-efficiency. You will work with AI researchers and ML engineers to improve stability of Cohere's foundation models.

The role emphasizes automation, on-call readiness, and collaboration across hardware partners. Strong Python/Go experience is valued, as is previous work with ML teams.