Job Description
Architect and implement robust integrations for large language models into the North platform, ensuring seamless scalability and performance. Collaborate with modelling teams to refine LLM performance, reduce latency, and improve accuracy through iterative testing and tuning. Develop and maintain tools for analysing and monitoring model performance, enabling data-driven improvements. Take end-to-end ownership of features — from initial design and planning, through implementation, testing, and delivery. Collaborate closely across teams, maintaining high standards for communication, documentation, and testing.
The tech stack includes Python, TypeScript with React, Postgres, and is deployed on Kubernetes. They value strong fundamentals and a learning mindset over specific tech experience. This role requires experience owning complex features from design to deployment, with a focus on scalability and maintainability.
About Cohere
Cohere's mission is to scale intelligence to serve humanity by training and deploying frontier models for developers and enterprises.