Remote Audio Inference Engineer — High-Performance Serving

Cohere; United States; Remote; USD 110,000 - 180,000; Full time

Benefits offered by this job

A weekly lunch stipend of $75/£75 or"

Job summary

Cohere is hiring an engineer to advance core audio model serving, latency, throughput, and quality for real-time streaming workloads. You will work across the model development and deployment stack with emphasis on C++/Python, GPU optimization, and ML frameworks in a remote-friendly, globally distributed setup.

You’ll collaborate with research and engineering to push frontier audio capabilities, applying attention to low-level optimizations and scalable inference systems across multiple GPUs.

Qualifications

• Significant experience developing high-performance audio or machine-learning inference systems.
• Proficiency with programming languages such as C++ and Python.
• Hands-on experience with deep learning models for audio, speech, or language applications.

Responsibilities

• Develop and optimize high-performance audio and ML inference systems for real-time streaming workloads.
• Collaborate with training and serving teams to integrate model development with deployment.
• Improve latency, throughput, and quality of audio processing pipelines.

Skills

Audio ML inference

C++

Python

Deep learning for audio

GPU programming

Streaming architectures

PyTorch/TensorFlow

Tools

vLLM

SGLang

Tensort-LLM

Job description

Cohere is hiring an engineer to advance core audio model serving, latency, throughput, and quality for real-time streaming workloads. You will work across the model development and deployment stack with emphasis on C++/Python, GPU optimization, and ML frameworks in a remote-friendly, globally distributed setup.

You’ll collaborate with research and engineering to push frontier audio capabilities, applying attention to low-level optimizations and scalable inference systems across multiple GPUs.