Staff Research Engineer, Model Efficiency
New York, San Francisco, Toronto, Montreal
Workplace: HybridFull timeFunction: Research & Scientific (R&D)Education: phdSkills: ["Communication","Problem-solving","Team collaboration"]Lead research and engineering efforts to accelerate inference efficiency for Cohere’s foundation models. Develop, prototype, and deploy techniques to speed up model runtime, optimize MoE routing and decoding, and collaborate across a distributed team to push the boundaries of AI performance in production.
Loading
Loading job details...
Preparing the role view and application actions.

