Job · Cohere
Member of Technical Staff, Model Efficiency
| Employer | Cohere |
|---|---|
| Location | New York (remote) |
| Type | Full-time |
| Pay (as disclosed) | CAD 250,000–CAD 535,000 per year |
| Posted | 7 Nov 2025 |
About the role
Cohere is hiring a Member of Technical Staff, Model Efficiency to optimize large language model inference performance. The role involves identifying execution bottlenecks and developing optimizations across the inference stack to improve latency and throughput. Candidates need five years of high-performance coding experience, strong C++ or Python skills, and familiarity with the LLM inference ecosystem.
Summary written by GAR, Octum’s cognitive engine, from the employer’s posting. The full description is on the employer’s site.
More roles at Cohere
Collected by Octum from Cohere’s careers site on 31 Oct 2026; Octum is not the employer and does not take applications. Spotted something wrong? Tell us.