Audio Inference Engineer, Model Efficiency at Cohere
Confirmed open
Improve latency, throughput and quality of real-time audio model inference at Cohere. The remote-friendly Model Efficiency team prefers overlap with Eastern or Pacific time zones.
- Location
- Remote
- Advertised region
- New York / San Francisco / Toronto / Montreal / United States
- Employment
- FullTime
- Work arrangement
- remote
- Technologies
- Python, C++, PyTorch, TensorFlow
Create a free application profile — Keep your skills and projects in a reusable profile. Private by default; you choose when to share. Apply for this job directly with the employer.
Role overview
Improve latency, throughput and quality of real-time audio model inference at Cohere. The remote-friendly Model Efficiency team prefers overlap with Eastern or Pacific time zones.
Responsibilities
- Find bottlenecks in speech and audio serving systems.
- Optimize streaming inference and coordinate changes with model training and serving infrastructure teams.
- Measure performance and quality of deployed audio workloads.
Qualifications
- Experience building high-performance audio or ML inference systems.
- C++ or Python skills and practical work with deep-learning models for speech, audio or language.
Technology in this role
- Python: C++ or Python skills and practical work with deep-learning models for speech, audio or language.
About Cohere
Cohere builds foundation AI models and enterprise AI products.
Employer websiteHow to apply
Review the original posting and apply through the employer’s careers page.
View source and applyApply directlySource checked: 2026-10-17