
Audio Inference Engineer, Model Efficiency

Audio Inference Engineer, Model Efficiency
Cohere
Cohere is seeking an Audio Inference Engineer to enhance machine learning systems focused on audio inference efficiency. The role involves optimizing audio model serving metrics and collaborating with infrastructure teams to ensure effective model deployment. The company values diverse perspectives and offers a remote-friendly work environment across various global locations.
Qualification
- Significant experience in developing audio or machine learning inference systems
- Proficiency in programming languages such as C++ and Python
- Hands-on experience with deep learning models for audio, speech, or language applications
- Strong results-oriented mindset and bias for action
Responsibility
- Develop high-performance audio or machine learning inference systems
- Optimize audio inference serving efficiency using innovative techniques
- Advance core audio model serving metrics including latency, throughput, and quality
- Identify bottlenecks in systems and deliver creative solutions for audio processing
- Collaborate with training and serving infrastructure teams for seamless model integration



