Staff Research Engineer: Accelerate LLM Inference (Remote)

montreal, montreal (administrative region), Canada • Posted June 03, 2026

Job Type: Full-time
Location: montreal, montreal (administrative region)
Posted: June 03, 2026
Category: Engineering
Application Deadline: July 13, 2026

Role Description

A leading AI research firm in Montreal is seeking a Staff Research Engineer to enhance model efficiency and optimize inference for large language models. In this full-time role, you will develop techniques to improve performance while maintaining model quality. The ideal candidate will hold a PhD in Machine Learning, with strong software engineering skills and experience in AI research. The position offers a collaborative remote-friendly environment along with numerous benefits.
#J-18808-Ljbffr

Interested in this role?

Click the button below to start your application for Staff Research Engineer: Accelerate LLM Inference (Remote) at Cohere.

Apply Now