# Audio Inference Engineer, Model Efficiency

Hiring organization: [Cohere](https://career.thegoodapps.co/organizations/cohere)

Canonical page: https://career.thegoodapps.co/jobs/e31d7c8a-08d1-4492-9f2b-820f4be95513

Listed on Cohere's own careers site. Applications go to them directly.

- Employment type: full time
- Location: New York, NY
- Remote: yes
- Salary: 250000 – 535000 CAD per year

## Summary

Cohere seeks an engineer to optimize audio model inference performance across latency, throughput, and quality metrics. This role suits someone with deep systems expertise in machine learning inference who can identify bottlenecks and deliver solutions for real-time audio processing at scale.

_Our summary, not Cohere's wording._

## Skills named

C++, Python, PyTorch, TensorFlow

## Required

- High-performance audio or machine learning inference systems development
- C++ and Python proficiency
- Deep learning models for audio, speech, or language applications
- Results-oriented mindset

## Nice to have

- GPU programming and low-level system optimization
- Model parallelization across multiple GPUs
- Duplex real-time streaming architectures
- Machine learning framework internals for audio
- Custom distributed inference systems
- Transformers and sequence modeling for audio/speech
- End-to-end audio pipeline optimization

Apply on Cohere's site: https://jobs.ashbyhq.com/cohere/e912d84c-8399-422d-8a7d-918422a3e4b1/application