PRF·0017

Software Engineer, GPU Infrastructure (HPC)

Cohere · Canada, United States

Kernel & DriversNetworking & ProtocolsPerformance & Observability

Summary

Cohere is hiring a Software Engineer, GPU Infrastructure (HPC) in Canada. The role focuses on operating systems & kernel, networking, graphics, gpu & compute, low-latency & performance.

Responsibilities as stated

  • Build and scale ML-optimized HPC infrastructure: Deploy and manage Kubernetes-based GPU/TPU superclusters across multiple clouds, ensuring high throughput and low-latency performance for AI workloads.
  • Low-level systems knowledge: Familiarity with Linux internals, RDMA networking, and performance optimization for ML workloads.
  • Deep expertise in ML/HPC infrastructure: Experience with GPU/TPU clusters, distributed training frameworks (JAX, PyTorch, TensorFlow), and high-performance computing (HPC) environments.

Location, employment, and compensation

  • Location. Canada, United States — hybrid
  • Employment. unknown
  • Compensation. Not stated on the source. NearMetal does not estimate compensation.
  • How to apply. On the company’s own posting. NearMetal does not accept applications.

Why this is filed as systems software

  • Build and scale ML-optimized HPC infrastructure: Deploy and manage Kubernetes-based GPU/TPU superclusters across multiple clouds, ensuring high throughput and low-latency performance for AI workloads.
  • Low-level systems knowledge: Familiarity with Linux internals, RDMA networking, and performance optimization for ML workloads.
  • Deep expertise in ML/HPC infrastructure: Experience with GPU/TPU clusters, distributed training frameworks (JAX, PyTorch, TensorFlow), and high-performance computing (HPC) environments.

Source and corrections

This summary was written from the company’s own posting. NearMetal does not reproduce the full description and does not accept applications.

Open the company posting ↗

LAST UPDATED 2h263 roles80 companiesnext check 10h263 roles · updated 2hindex status ↗