Research Scientist in AI Evaluation

Cohere is seeking a Senior Research Scientist focused on AI evaluation methods to support our innovative foundation models. This remote or on-site role emphasizes creating evaluation benchmarks and tools that enhance LLM capabilities.

As a Senior Research Scientist at Cohere, you will lead the development of next-generation evaluation techniques critical for AI model scaling. Collaborate with cross-functional teams to refine model feedback and improve evaluation processes. Your contributions will be pivotal in advancing the standards for assessing AI performance and capability alignment.

Key Responsibilities:

• Create ambitious new evaluation benchmarks for AI models

• Collaborate cross-functionally for trustworthy evaluations

• Conduct research on LLM evaluation methods

• Develop scalable tools for performance analysis

Requirements:

• Experience in building AI prototypes and evaluations

• Proficiency in data review for quality assurance

• Commitment to rigorous measurement practices

• Strong software engineering skills

Drive innovation in AI evaluation techniques with your expertise at Cohere and significantly impact model performance.