Staff Research Engineer, Model Efficiency

Cohere(2 months ago)

HybridFull TimeSenior$182,675 - $243,551 (estimated)Modeling

About this role

The Staff Research Engineer, Model Efficiency at Cohere is responsible for enhancing the inference efficiency of Large Language Models (LLMs) within AI systems. This role involves developing and deploying novel techniques to optimize model architecture, decoding algorithms, and software/hardware co-design for GPU acceleration. Candidates should possess a PhD in Machine Learning, significant experience in model efficiency techniques, strong software engineering skills, and a background in research publications.

View Original Listing

Required Skills

Large Language Models
Model Architecture
Optimization Techniques
Inference Efficiency
Software Engineering
Fast-Paced Environment
Research Publications
Mentoring Skills

Qualifications

PhD in Machine Learning or a related field
Publications at top-tier conferences and venues (ICLR, ACL, NeurIPS)

About Cohere

cohere.com

Sanity is a platform that provides flexible content management solutions tailored for developers, marketers, and content creators. By utilizing a real-time collaborative editor and structured content, it allows users to build and manage high-performance applications and websites. Sanity’s APIs and flexible data model enable seamless integration with various frameworks and technologies, empowering users to deliver customized content experiences. With features like query-driven content fetching and an extensible plugin system, Sanity is designed to enhance productivity and scalability for teams of all sizes.