Specialty
The role
Cohere, an enterprise AI company, is hiring a Staff Research Engineer for its Model Efficiency team to make LLM inference faster and cheaper across its foundation models. The team is concentrated in EST and PST time zones; remote work is allowed.
What you will do
- Develop, prototype and deploy techniques that improve how fast and efficiently models run in production.
- Work on model architecture and MoE routing optimization.
- Improve decoding and inference-time algorithms.
- Co-design software and hardware for GPU acceleration without hurting model quality.
What they ask for
- PhD in Machine Learning or a related field.
- Understanding of LLM architecture and how to optimize inference under resource constraints.
- Significant experience with one or more model efficiency techniques.
- Strong software engineering skills.
- Comfort with a fast-paced, ambiguous start-up environment.
- Publications at top venues such as ICLR, ACL or NeurIPS, and a passion for mentoring.
- Preferably based in the EST or PST time zones.
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.
