jobs

Audio Inference Engineer, Model Efficiency

Who are we?Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.We’re training and deploying frontier models f

In inglese

Company

Cohere

Location

New York; San Francisco; Toronto; Montreal

Status

Open

Posted

2025-11-07T23:33:54.457+00:00

Cohere is hiring an Audio Inference Engineer for its Model Efficiency team to improve audio model serving. The person will find bottlenecks and work on latency, throughput, and quality for audio and real-time streaming inference, alongside training and serving infrastructure teams. The posting asks for experience with high-performance audio or ML inference, C++, Python, and deep learning for audio, speech, or language. GPU programming, multi-GPU parallelization, and frameworks like vLLM or SGLang are pluses. The role is remote-friendly, with the team concentrated in EST and PST time zones.