Applied MLE Engineer, North Modelling Evals

Cohere; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Lunch stipend

Health benefits

RRSP matching

Parental leave top-up

Enrichment benefits

Vacation

Office travel budget

Job summary

Cohere is seeking a Member of Technical Staff, North Modelling (Evals) to build evaluation systems and feedback loops for North. You will translate user and product needs into high-quality evals and guide model updates, working with product, customer-facing, and modelling teams.

This role sits at the intersection of applied MLE and product quality, requiring practical judgement, data-driven experimentation, and a passion for measuring real-world impact in enterprise AI workflows.

Qualifications

• Must design evaluation systems for enterprise AI products.
• Experience turning customer needs into measurable evals.
• Ability to reason about model behavior and production tradeoffs.

Responsibilities

• Own the eval strategy for North: define what to measure across agent workflows and enterprise knowledge work.
• Build high-quality evals from real product signals: user feedback, production failures, logs, customer needs.
• Create systems that continually turn learnings into evals and guide product direction.
• Be the voice of North inside modelling: translate eval results into actionable recommendations.

Skills

Eval systems design

Data curation

Model evaluation

Applied MLE judgment

Cross-functional collaboration

Job description

Cohere is seeking a Member of Technical Staff, North Modelling (Evals) to build evaluation systems and feedback loops for North. You will translate user and product needs into high-quality evals and guide model updates, working with product, customer-facing, and modelling teams.

This role sits at the intersection of applied MLE and product quality, requiring practical judgement, data-driven experimentation, and a passion for measuring real-world impact in enterprise AI workflows.