Specialty
The role
Cohere, an enterprise AI company, is hiring an Audio Inference Engineer for its Model Efficiency team to improve latency, throughput and quality of audio model serving, with a focus on real-time streaming. The team is concentrated in EST and PST time zones; remote work is allowed.
What you will do
- Advance core audio model serving metrics: latency, throughput and quality.
- Find bottlenecks in audio processing and streaming systems and deliver fixes.
- Work with the training and serving infrastructure teams to connect model development with deployment.
- Focus on real-time and streaming audio inference.
What they ask for
- Significant experience developing high-performance audio or machine learning inference systems.
- Proficiency in C++ and Python.
- Hands-on experience with deep learning models for audio, speech or language.
- Results-oriented mindset with a bias for action.
- Preferably based in the EST or PST time zones.
- Nice to have: GPU programming, duplex real-time streaming, and vLLM, SGLang or TensorRT-LLM experience.
What they offer
- Weekly lunch stipend
- Health and dental benefits with a mental health budget
- RRSP matching, 401(k) or pension
- Parental leave top-up for up to 6 months
- 6 weeks paid vacation
- $500 home office stipend and co-working benefit
This is our own short reading of the posting. The full description, and anything that has changed since, is on Cohere's careers page behind the apply button.
