TechPrufer
Sign inGet started

Blogs›LinkedIn›Internationalization of Agentic AI Systems

Internationalization of Agentic AI Systems

Internationalization of Agentic AI Systems

1
posts
2026

This post details the process and challenges of internationalizing LinkedIn's Hiring Assistant, an agentic AI product, for French and German markets. It highlights the difficulties of on-the-fly text generation compared to traditional software localization, focusing on linguistic nuances like gender agreement, formal/informal address, noun capitalization, and number/date formats. The solution involves a shared rubric framework to capture language-specific rules, per-language Low-rank Adaptation (LoRA) adapters for efficient model adaptation, and an automated prompt transformation pipeline. The post emphasizes the need for explicit handling of language nuances, scaling linguist annotation for measurement, and managing the complexity of prompt evolution across multiple languages and sub-agents.

2026

Engineering LinkedIn's Hiring Assistant for International Markets

6/8/2026

Introduces a playbook for internationalizing agentic AI systems, focusing on the challenges of on-the-fly text generation. Details a solution involving a shared rubric framework to capture language-specific rules and per-language LoRA adapters to adapt smaller models efficiently. Discusses the need for explicit handling of language nuances, scaling linguist annotation, and managing prompt evolution across multiple languages and sub-agents.