C
$190,000 – $325,000
Listed on Cohere’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
Cohere seeks a Staff Software Engineer to build and operate the inference infrastructure powering their enterprise AI models, focusing on high-performance distributed systems and GPU workload orchestration. This role suits experienced infrastructure engineers who excel at designing large-scale Kubernetes deployments and optimizing systems for low-latency, high-throughput production environments.
Our summary, not Cohere’s wording. The full posting is on their site.
Skills this role names
Log in to see which of these are already on your profile.
What they ask for
Required
- 5+ years of production infrastructure engineering at scale
- Kubernetes design and production experience
- Large distributed systems architecture
- GPU workload cluster management
- Linux-based computing environment design and troubleshooting
- Compute, storage, and network resource optimization
Nice to have
- Experience with multiple cloud platforms (GCP, Azure, AWS, OCI)
- Hybrid or on-prem infrastructure serving
- Familiarity with GPU, TPU, or custom accelerators
- Knowledge of inference latency and throughput optimization
- Golang or C++ experience for high-performance servers